Universal Agent Context — 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": "universal-agent-context",
"source": {
"kind": "package",
"origin": "universal-agent-context"
},
"server": {
"name": "universal-agent-context"
}
},
"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": [
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (21 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 (.claude-plugin/test_hook.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`.claude-plugin/test_hook.py:69`): 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": ".claude-plugin/test_hook.py"
},
"evidence": "try: result = subprocess.run( [\"python3\", \".claude-plugin/hooks/uacs_store.py\"], input",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude-plugin/test_hook.py",
"line": 69,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/uacs/packages/manager.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/uacs/packages/manager.py:114`): 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/uacs/packages/manager.py"
},
"evidence": "try: subprocess.run( [\"git\", \"clone\", \"--depth\", \"1\", url, str(dest)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/uacs/packages/manager.py",
"line": 114,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/uacs/packages/sources.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/uacs/packages/sources.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/uacs/packages/sources.py"
},
"evidence": "one command subprocess.run( [\"git\", \"clone\", \"--depth\", \"1\", url, str(target_dir)],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/uacs/packages/sources.py",
"line": 158,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (tools/build_mcp_server.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tools/build_mcp_server.py:94`): 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": "tools/build_mcp_server.py"
},
"evidence": "stderr result = subprocess.run( pyinstaller_args, check=True, capture_output",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tools/build_mcp_server.py",
"line": 94,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "skills_list",
"tags": [],
"reasons": {}
},
{
"tool": "skills_show",
"tags": [],
"reasons": {}
},
{
"tool": "skills_test_trigger",
"tags": [],
"reasons": {}
},
{
"tool": "skills_validate",
"tags": [],
"reasons": {}
},
{
"tool": "context_stats",
"tags": [],
"reasons": {}
},
{
"tool": "context_get_compressed",
"tags": [],
"reasons": {}
},
{
"tool": "context_add_entry",
"tags": [],
"reasons": {}
},
{
"tool": "context_compress",
"tags": [],
"reasons": {}
},
{
"tool": "context_graph",
"tags": [],
"reasons": {}
},
{
"tool": "agents_md_load",
"tags": [],
"reasons": {}
},
{
"tool": "agents_md_to_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "unified_build_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "unified_capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "unified_token_stats",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"get_token\""
]
}
},
{
"tool": "install_package",
"tags": [],
"reasons": {}
},
{
"tool": "list_installed_packages",
"tags": [],
"reasons": {}
},
{
"tool": "validate_package",
"tags": [],
"reasons": {}
},
{
"tool": "project_validate",
"tags": [],
"reasons": {}
},
{
"tool": "uacs_search_context",
"tags": [],
"reasons": {}
},
{
"tool": "uacs_list_topics",
"tags": [],
"reasons": {}
},
{
"tool": "uacs_get_recent_sessions",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "d4426ee0ed8d767ad42b356a89271aa561781548032bbf378b119c1160354103",
"stats": {
"tools": 21,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 3,
"medium": 0,
"low": 1,
"info": 0
}
}
}