Agency Orchestrator MCP Server
agency-orchestrator
npm
v0.12.1
Published by jnmetacode — no publish provenance and no vendor-owned scope, so the publisher could not be verified. The repository link below is self-declared.
Every server starts at 100. These are the exact deductions the deterministic engine applied — each one reproducible, none of it an opinion or an LLM's guess:
| Points | What was found | Category |
|---|---|---|
| −12.9 | Unsafe deserialization ×6 MTC-SRC-007 | permissions |
| −9.5 | Untrusted input concatenated into a command sink ×2 MTC-SRC-009 | injection |
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 the deduction.
Findings 17
high Dynamic code execution in server code (website/dist/assets/vendor-charts-EdNYpIP7.js)MTC-SRC-001
In the server's implementation (`website/dist/assets/vendor-charts-EdNYpIP7.js:1`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: Function("
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 website/dist/assets/vendor-charts-EdNYpIP7.js
high Shell/command execution in server code (dist/cli.js)MTC-SRC-002
In the server's implementation (`dist/cli.js:14`): 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/cli.js
high Shell/command execution in server code (dist/cli/demo.js)MTC-SRC-002
In the server's implementation (`dist/cli/demo.js:31`): 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/cli/demo.js
high Shell/command execution in server code (dist/connectors/claude-code.js)MTC-SRC-002
In the server's implementation (`dist/connectors/claude-code.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/connectors/claude-code.js
high Shell/command execution in server code (dist/connectors/cli-base.js)MTC-SRC-002
In the server's implementation (`dist/connectors/cli-base.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 dist/connectors/cli-base.js
high Shell/command execution in server code (dist/export/convert.js)MTC-SRC-002
In the server's implementation (`dist/export/convert.js:8`): 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/export/convert.js
high Shell/command execution in server code (web/server.js)MTC-SRC-002
In the server's implementation (`web/server.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 web/server.js
medium Hardcoded egress to an external endpoint (dist/utils/version-check.js)MTC-SRC-003
In the server's implementation (`dist/utils/version-check.js:48`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch(`https://registry.npmjs.org/${PKG}/latest`
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/utils/version-check.js
medium Hardcoded egress to an external endpoint (web/server.js)MTC-SRC-003
In the server's implementation (`web/server.js:1781`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: fetch('https://api.anthropic.com/v1/messages'
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 web/server.js
medium Untrusted input concatenated into a command sink (dist/cli.js)MTC-SRC-009
In the server's implementation (`dist/cli.js:1270`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: execSync(`npm pack ${
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/cli.js
medium Untrusted input concatenated into a command sink (dist/cli/demo.js)MTC-SRC-009
In the server's implementation (`dist/cli/demo.js:32`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: execSync(`which ${
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/cli/demo.js
medium Unsafe deserialization (dist/canvas/graph.js)MTC-SRC-007
In the server's implementation (`dist/canvas/graph.js:13`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: yaml.load(
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/canvas/graph.js
medium Unsafe deserialization (dist/cli/compose.js)MTC-SRC-007
In the server's implementation (`dist/cli/compose.js:49`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: yaml.load(
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/cli/compose.js
medium Unsafe deserialization (dist/cli/team.js)MTC-SRC-007
In the server's implementation (`dist/cli/team.js:72`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: yaml.load(
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/cli/team.js
medium Unsafe deserialization (dist/core/parser.js)MTC-SRC-007
In the server's implementation (`dist/core/parser.js:10`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: yaml.load(
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/core/parser.js
medium Unsafe deserialization (dist/mcp/server.js)MTC-SRC-007
In the server's implementation (`dist/mcp/server.js:66`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: yaml.load(
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/mcp/server.js
medium Unsafe deserialization (web/server.js)MTC-SRC-007
In the server's implementation (`web/server.js:396`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: yaml.load(
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 web/server.js
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|---|---|
v0.12.1 latest |
C 78/100 | 17 | 1.5.0 | 2026-07-22 |
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 agency-orchestrator --onlineMore in Developer Tools
Security scan results for the 199bio Mcp Limitless MCP server.
Security scan results for the 1mcp MCP server.
Security scan results for the 1stay MCP server.
Generates production-ready UI components from natural language, inspired by v0.
Security scan results for the 2slides MCP server.
Security scan results for the 3d MCP server.