Agents Remember — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "agents-remember-mcp",
"source": {
"kind": "package",
"origin": "agents-remember-mcp"
},
"server": {
"name": "agents-remember-mcp"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (36 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/agents_remember/code_quality/check.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/code_quality/check.py:47`): 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/agents_remember/code_quality/check.py"
},
"evidence": "Result: completed = subprocess.run( command, cwd=cwd, env=dict(env), stdin=subprocess.DEVNULL, check=False",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/code_quality/check.py",
"line": 47,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/kernel/git_command.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/kernel/git_command.py: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.",
"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/agents_remember/kernel/git_command.py"
},
"evidence": "rocess[str]: return subprocess.run( [\"git\", \"-c\", f\"safe.directory={repo_root.as_posix()}\", *args],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/kernel/git_command.py",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/kernel/git_freshness.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/kernel/git_freshness.py:42`): 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/agents_remember/kernel/git_freshness.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"-c\", f\"safe.directory={repo_root.as_posix()}\", \"fetch\", rem",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/kernel/git_freshness.py",
"line": 42,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/kernel/memory_init.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/kernel/memory_init.py:44`): 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/agents_remember/kernel/memory_init.py"
},
"evidence": "return git result = subprocess.run( [\"git\", \"init\"], cwd=memory_root, text=True, std",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/kernel/memory_init.py",
"line": 44,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/memory/carryover.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/memory/carryover.py:99`): 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/agents_remember/memory/carryover.py"
},
"evidence": "VNULL} ) return subprocess.run( [\"git\", \"-c\", f\"safe.directory={repo.as_posix()}\", *args], cwd=r",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/memory/carryover.py",
"line": 99,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/memory_quality/integrity/check_missing_onboarding.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/memory_quality/integrity/check_missing_onboarding.py:161`): 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/agents_remember/memory_quality/integrity/check_missing_onboarding.py"
},
"evidence": "cess[str]: result = subprocess.run( [\"git\", \"-c\", f\"safe.directory={repo_root.as_posix()}\", *args],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/memory_quality/integrity/check_missing_onboarding.py",
"line": 161,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/memory_quality/integrity/onboarding_drift_check/git_ops.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/memory_quality/integrity/onboarding_drift_check/git_ops.py:16`): 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/agents_remember/memory_quality/integrity/onboarding_drift_check/git_ops.py"
},
"evidence": "rocess[str]: return subprocess.run( [\"git\", \"-c\", f\"safe.directory={repo_root.as_posix()}\", *args],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/memory_quality/integrity/onboarding_drift_check/git_ops.py",
"line": 16,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/agents_remember/providers/cgc/seed.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/agents_remember/providers/cgc/seed.py:201`): 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/agents_remember/providers/cgc/seed.py"
},
"evidence": "eturn None result = subprocess.run( [ \"git\", \"-c\", f\"safe.directory={rep",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/providers/cgc/seed.py",
"line": 201,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (src/agents_remember/benchmarks/runner_modules/commands.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/agents_remember/benchmarks/runner_modules/commands.py:16`): 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/agents_remember/benchmarks/runner_modules/commands.py"
},
"evidence": "tHub #49). result = subprocess.run( command, cwd=cwd, check=False, stdin=subprocess.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/benchmarks/runner_modules/commands.py",
"line": 16,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (src/agents_remember/benchmarks/runner_modules/execution.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`src/agents_remember/benchmarks/runner_modules/execution.py:251`): 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/agents_remember/benchmarks/runner_modules/execution.py"
},
"evidence": "): completed = subprocess.run( command, input=prompt_text, stdout=stdout,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/agents_remember/benchmarks/runner_modules/execution.py",
"line": 251,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"agents-remember-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "agents-remember-mcp"
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"agents-remember-mcp\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "agents-remember-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "ping",
"tags": [],
"reasons": {}
},
{
"tool": "server_info",
"tags": [],
"reasons": {}
},
{
"tool": "context_packet",
"tags": [],
"reasons": {}
},
{
"tool": "runtime_install",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_context",
"tags": [],
"reasons": {}
},
{
"tool": "drift_check",
"tags": [],
"reasons": {}
},
{
"tool": "memory_quality_check",
"tags": [],
"reasons": {}
},
{
"tool": "route_index_refresh",
"tags": [],
"reasons": {}
},
{
"tool": "memory_init",
"tags": [],
"reasons": {}
},
{
"tool": "skills_install",
"tags": [],
"reasons": {}
},
{
"tool": "provider_status",
"tags": [],
"reasons": {}
},
{
"tool": "provider_diagnostics",
"tags": [],
"reasons": {}
},
{
"tool": "provider_watchers",
"tags": [],
"reasons": {}
},
{
"tool": "grepai_search",
"tags": [],
"reasons": {}
},
{
"tool": "grepai_trace",
"tags": [],
"reasons": {}
},
{
"tool": "cgc_symbol_search",
"tags": [],
"reasons": {}
},
{
"tool": "cgc_callers",
"tags": [],
"reasons": {}
},
{
"tool": "cgc_callees",
"tags": [],
"reasons": {}
},
{
"tool": "cgc_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "cgc_complexity",
"tags": [],
"reasons": {}
},
{
"tool": "cgc_visualize",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_start",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_attach",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_status",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_sync",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_closeout_preview",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_closeout_apply",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_integrate",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_cleanup",
"tags": [],
"reasons": {}
},
{
"tool": "worktree_abandon",
"tags": [],
"reasons": {}
},
{
"tool": "memory_baseline_status",
"tags": [],
"reasons": {}
},
{
"tool": "memory_baseline_adopt",
"tags": [],
"reasons": {}
},
{
"tool": "memory_carryover_plan",
"tags": [],
"reasons": {}
},
{
"tool": "memory_carryover_apply",
"tags": [],
"reasons": {}
},
{
"tool": "codex_benchmark_prepare",
"tags": [],
"reasons": {}
},
{
"tool": "codex_benchmark_run",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "12adf821648269afc53227d72bd61d8d8a6862dc6446e4f3d381a5561174800e",
"stats": {
"tools": 36,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 2,
"info": 2
}
}
}