Safe Bifrost MCP Server
safe-bifrost
npm
v0.3.0
Published by jiezeng2004-design — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 11 = 89. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −10 | capability blast radius (critical) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
| ✓ | inspection depth (source) — how much of the target the scan could see |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 26
critical Completed toxic-flow trifecta across toolsMTC-FLOW-002
This server (without client built-ins) exposes a complete data-exfiltration chain: get_task_progress → create_task. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.
Fix: Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.
Location: flow get_task_progress → create_task
high Read-and-egress in one tool: "create_task"MTC-FLOW-003
Tool "create_task" can both read sensitive data and send data to an external destination. Even without an explicit untrusted-input leg, this is a single-call data-exfiltration path if the model is ever manipulated.
Fix: Separate reading from sending; require explicit user confirmation before egress of file/secret contents.
Location: flow create_task
high Reads a sensitive credential path or dumps the environment (dist/doctor.js)MTC-SRC-006
In the server's implementation (`dist/doctor.js:159`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/doctor.js
high Reads a sensitive credential path or dumps the environment (dist/security/planGuard.js)MTC-SRC-006
In the server's implementation (`dist/security/planGuard.js:6`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/security/planGuard.js
high Reads a sensitive credential path or dumps the environment (dist/security/sensitiveGuard.js)MTC-SRC-006
In the server's implementation (`dist/security/sensitiveGuard.js:10`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/security/sensitiveGuard.js
high Reads a sensitive credential path or dumps the environment (dist/smoke-test.js)MTC-SRC-006
In the server's implementation (`dist/smoke-test.js:217`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/smoke-test.js
high Reads a sensitive credential path or dumps the environment (src/doctor.ts)MTC-SRC-006
In the server's implementation (`src/doctor.ts:173`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/doctor.ts
high Reads a sensitive credential path or dumps the environment (src/security/planGuard.ts)MTC-SRC-006
In the server's implementation (`src/security/planGuard.ts:14`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/security/planGuard.ts
high Reads a sensitive credential path or dumps the environment (src/security/sensitiveGuard.ts)MTC-SRC-006
In the server's implementation (`src/security/sensitiveGuard.ts:11`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/security/sensitiveGuard.ts
high Reads a sensitive credential path or dumps the environment (src/smoke-test.ts)MTC-SRC-006
In the server's implementation (`src/smoke-test.ts:243`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: id_rsa
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/smoke-test.ts
high Tool "create_task" exposes command/code executionMTC-CAP-001
Tool "create_task" appears to run shell commands or evaluate code (parameter "command"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool create_task
high Shell/command execution in server code (dist/doctor.js)MTC-SRC-002
In the server's implementation (`dist/doctor.js:12`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/doctor.js
high Shell/command execution in server code (dist/runner/changeCapture.js)MTC-SRC-002
In the server's implementation (`dist/runner/changeCapture.js:4`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/runner/changeCapture.js
high Shell/command execution in server code (dist/runner/runTask.js)MTC-SRC-002
In the server's implementation (`dist/runner/runTask.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/runner/runTask.js
high Shell/command execution in server code (dist/smoke-test.js)MTC-SRC-002
In the server's implementation (`dist/smoke-test.js:19`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/smoke-test.js
high Shell/command execution in server code (src/doctor.ts)MTC-SRC-002
In the server's implementation (`src/doctor.ts:13`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server src/doctor.ts
medium Unconstrained command parameter "test_command" on "create_task"MTC-CAP-006
Tool "create_task" takes a command-shaped parameter "test_command" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool create_task · inputSchema.properties.test_command
low Mutating tool "create_task" declares no destructiveHintMTC-CAP-005
Tool "create_task" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool create_task
low Unconstrained path parameter "repo_path" on "create_task"MTC-CAP-008
Tool "create_task" takes a path parameter "repo_path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool create_task · inputSchema.properties.repo_path
low Unconstrained path parameter "path" on "list_workspace"MTC-CAP-008
Tool "list_workspace" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool list_workspace · inputSchema.properties.path
low Unconstrained path parameter "path" on "read_workspace_file"MTC-CAP-008
Tool "read_workspace_file" takes a path parameter "path" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.
Fix: Resolve and verify the path stays within an allowed root; reject traversal sequences.
Location: tool read_workspace_file · inputSchema.properties.path
low Shell/command execution in packaging/dev tooling (scripts/doctor-smoke.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/doctor-smoke.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/doctor-smoke.js
low Shell/command execution in packaging/dev tooling (scripts/http-mcp-smoke.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/http-mcp-smoke.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/http-mcp-smoke.js
low Shell/command execution in packaging/dev tooling (scripts/lifecycle-smoke.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/lifecycle-smoke.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/lifecycle-smoke.js
low Shell/command execution in packaging/dev tooling (scripts/mcp-smoke.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/mcp-smoke.js:2`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/mcp-smoke.js
low Shell/command execution in packaging/dev tooling (scripts/pack-clean.js)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/pack-clean.js:10`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: child_process
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/pack-clean.js
Tools 22
Each tool and what it can reach — statically extracted from the published source.
create_taskruns code / shellreads sensitive dataget_task_progressingests untrusted inputlist_workspacereads sensitive dataread_workspace_filereads sensitive dataaudit_taskno sensitive capabilitycancel_taskno sensitive capabilityget_diffno sensitive capabilityget_planno sensitive capabilityget_resultno sensitive capabilityget_result_jsonno sensitive capabilityget_task_statusno sensitive capabilityget_task_stdout_tailno sensitive capabilityget_task_summaryno sensitive capabilityget_test_logno sensitive capabilityhealth_checkno sensitive capabilitykill_taskno sensitive capabilitylist_agentsno sensitive capabilitylist_tasksno sensitive capabilityretry_taskno sensitive capabilityrun_taskno sensitive capabilitysave_planno sensitive capabilitywait_for_taskno sensitive capability
Toxic flows 2
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (22 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.3.0 latest |
B 89/100 | 26 | 1.8.0 | 2026-07-23 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan safe-bifrost --onlineMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Agent MCP server.