Canopy Cli — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "canopy-cli",
"source": {
"kind": "package",
"origin": "canopy-cli"
},
"server": {
"name": "canopy-cli"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.9"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"external-sink",
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (70 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>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/actions/bootstrap.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/actions/bootstrap.py:182`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/actions/bootstrap.py"
},
"evidence": ".monotonic() proc = subprocess.run( install_cmd, shell=True, cwd=worktree_path, capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/actions/bootstrap.py",
"line": 182,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/actions/doctor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/actions/doctor.py:893`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/actions/doctor.py"
},
"evidence": "try: out = subprocess.run( [\"ps\", \"-eo\", \"pid=,ppid=,command=\"], capture_output=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/actions/doctor.py",
"line": 893,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/agent/runner.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/agent/runner.py:46`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/agent/runner.py"
},
"evidence": "try: proc = subprocess.run( command, cwd=cwd, shell=True, ca",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/agent/runner.py",
"line": 46,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/cli/main.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/cli/main.py:1063`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/cli/main.py"
},
"evidence": "0]}\") try: subprocess.Popen( cmd, stdout=subprocess.DEVNULL, stderr=sub",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/cli/main.py",
"line": 1063,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/git/hooks.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/git/hooks.py:158`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/git/hooks.py"
},
"evidence": "unset.\"\"\" result = subprocess.run( [\"git\", \"config\", \"--get\", \"core.hooksPath\"], cwd=repo_path, cap",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/git/hooks.py",
"line": 158,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/git/repo.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/git/repo.py:32`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/git/repo.py"
},
"evidence": "g. \"\"\" result = subprocess.run( [\"git\"] + args, capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/git/repo.py",
"line": 32,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/git/templates/post-checkout.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/git/templates/post-checkout.py:29`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/git/templates/post-checkout.py"
},
"evidence": "return branch = subprocess.run( [\"git\", \"rev-parse\", \"--abbrev-ref\", \"HEAD\"], capture_output=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/git/templates/post-checkout.py",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/integrations/github.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/integrations/github.py:71`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/integrations/github.py"
},
"evidence": "turn False result = subprocess.run( [\"gh\", \"auth\", \"status\"], capture_output=True, text=True, check=False,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/integrations/github.py",
"line": 71,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/integrations/precommit.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/integrations/precommit.py:45`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/integrations/precommit.py"
},
"evidence": "k run` result = subprocess.run( [\"git\", \"rev-parse\", \"--git-common-dir\"], capture_output",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/integrations/precommit.py",
"line": 45,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/canopy/mcp/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/canopy/mcp/server.py:85`): 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.",
"remediation": "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": {
"kind": "server",
"name": "src/canopy/mcp/server.py"
},
"evidence": "try: out = subprocess.run( [cli_path, \"--version\"], capture_output=True, te",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/canopy/mcp/server.py",
"line": 85,
"nonRuntime": false
}
},
{
"ruleId": "MTC-FLOW-005",
"title": "Untrusted input can drive an external action",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "Untrusted-input tools ([github_get_pr, github_get_branch, github_get_pr_comments, pr_checks, review_comments, issue_get]) co-exist with external-action tools ([triage, review_comments]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.",
"remediation": "Require confirmation for state-changing/egress actions triggered after processing untrusted content.",
"location": {
"kind": "flow",
"name": "github_get_pr → triage"
},
"evidence": "untrusted [github_get_pr, github_get_branch, github_get_pr_comments, pr_checks, review_comments, issue_get] → sinks [triage, review_comments]",
"owasp": "LLM06:2025 Excessive Agency",
"references": [],
"data": {
"untrusted": [
"github_get_pr",
"github_get_branch",
"github_get_pr_comments",
"pr_checks",
"review_comments",
"issue_get"
],
"sinks": [
"triage",
"review_comments"
]
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"canopy-cli\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "canopy-cli"
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "medium",
"confidence": "strong",
"untrustedInput": [
"github_get_pr",
"github_get_branch",
"github_get_pr_comments",
"pr_checks",
"review_comments",
"issue_get"
],
"sensitiveSource": [],
"externalSink": [
"triage",
"review_comments"
],
"selfContained": false,
"description": "Untrusted input can drive an external action even though no sensitive source is exposed."
}
],
"capabilities": [
{
"tool": "version",
"tags": [],
"reasons": {}
},
{
"tool": "workspace_status",
"tags": [],
"reasons": {}
},
{
"tool": "context",
"tags": [],
"reasons": {}
},
{
"tool": "start",
"tags": [],
"reasons": {}
},
{
"tool": "join",
"tags": [],
"reasons": {}
},
{
"tool": "workspace_context",
"tags": [],
"reasons": {}
},
{
"tool": "run",
"tags": [],
"reasons": {}
},
{
"tool": "feature_state",
"tags": [],
"reasons": {}
},
{
"tool": "triage",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"open_pr\""
]
}
},
{
"tool": "switch",
"tags": [],
"reasons": {}
},
{
"tool": "slot_load",
"tags": [],
"reasons": {}
},
{
"tool": "slot_clear",
"tags": [],
"reasons": {}
},
{
"tool": "slot_swap",
"tags": [],
"reasons": {}
},
{
"tool": "commit",
"tags": [],
"reasons": {}
},
{
"tool": "bot_comments_status",
"tags": [],
"reasons": {}
},
{
"tool": "historian_decide",
"tags": [],
"reasons": {}
},
{
"tool": "historian_pause",
"tags": [],
"reasons": {}
},
{
"tool": "historian_defer_comment",
"tags": [],
"reasons": {}
},
{
"tool": "feature_memory",
"tags": [],
"reasons": {}
},
{
"tool": "historian_compact",
"tags": [],
"reasons": {}
},
{
"tool": "push",
"tags": [],
"reasons": {}
},
{
"tool": "stash_save_feature",
"tags": [],
"reasons": {}
},
{
"tool": "stash_list_grouped",
"tags": [],
"reasons": {}
},
{
"tool": "stash_pop_feature",
"tags": [],
"reasons": {}
},
{
"tool": "linear_get_issue",
"tags": [],
"reasons": {}
},
{
"tool": "github_get_pr",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "github_get_branch",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "github_get_pr_comments",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "doctor",
"tags": [],
"reasons": {}
},
{
"tool": "pr_checks",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "worktree_bootstrap",
"tags": [],
"reasons": {}
},
{
"tool": "ship",
"tags": [],
"reasons": {}
},
{
"tool": "draft_replies",
"tags": [],
"reasons": {}
},
{
"tool": "conflicts",
"tags": [],
"reasons": {}
},
{
"tool": "reply_to_thread",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_thread",
"tags": [],
"reasons": {}
},
{
"tool": "feature_resume",
"tags": [],
"reasons": {}
},
{
"tool": "drift",
"tags": [],
"reasons": {}
},
{
"tool": "feature_create",
"tags": [],
"reasons": {}
},
{
"tool": "feature_list",
"tags": [],
"reasons": {}
},
{
"tool": "feature_status",
"tags": [],
"reasons": {}
},
{
"tool": "feature_diff",
"tags": [],
"reasons": {}
},
{
"tool": "feature_changes",
"tags": [],
"reasons": {}
},
{
"tool": "feature_merge_readiness",
"tags": [],
"reasons": {}
},
{
"tool": "feature_paths",
"tags": [],
"reasons": {}
},
{
"tool": "checkout",
"tags": [],
"reasons": {}
},
{
"tool": "preflight",
"tags": [],
"reasons": {}
},
{
"tool": "log",
"tags": [],
"reasons": {}
},
{
"tool": "branch_list",
"tags": [],
"reasons": {}
},
{
"tool": "branch_delete",
"tags": [],
"reasons": {}
},
{
"tool": "branch_rename",
"tags": [],
"reasons": {}
},
{
"tool": "stash_save",
"tags": [],
"reasons": {}
},
{
"tool": "stash_pop",
"tags": [],
"reasons": {}
},
{
"tool": "stash_list",
"tags": [],
"reasons": {}
},
{
"tool": "stash_drop",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_info",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_create",
"tags": [],
"reasons": {}
},
{
"tool": "feature_done",
"tags": [],
"reasons": {}
},
{
"tool": "workspace_config",
"tags": [],
"reasons": {}
},
{
"tool": "review_status",
"tags": [],
"reasons": {}
},
{
"tool": "review_comments",
"tags": [
"untrusted-input",
"external-sink"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
],
"external-sink": [
"keyword \"open_pr\""
]
}
},
{
"tool": "review_prep",
"tags": [],
"reasons": {}
},
{
"tool": "workspace_reinit",
"tags": [],
"reasons": {}
},
{
"tool": "issue_get",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "issue_list_my_issues",
"tags": [],
"reasons": {}
},
{
"tool": "linear_my_issues",
"tags": [],
"reasons": {}
},
{
"tool": "feature_link_linear",
"tags": [],
"reasons": {}
},
{
"tool": "sync",
"tags": [],
"reasons": {}
},
{
"tool": "slots",
"tags": [],
"reasons": {}
},
{
"tool": "migrate_slots",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d1260e3c38d1ae6ab208344a56315a5a9397f36c9ded095ff617fd2c69eafa78",
"stats": {
"tools": 70,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 1,
"low": 0,
"info": 1
}
}
}