Serena Agent — 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": "serena-agent",
"source": {
"kind": "package",
"origin": "serena-agent"
},
"server": {
"name": "serena-agent"
}
},
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"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>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (repo_dir_sync.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`repo_dir_sync.py:57`): 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": "repo_dir_sync.py"
},
"evidence": "ath(os.getcwd())}\") os.system(f\"git commit --file={commitMsgFilename}\") os.unlink(commitMsgFilename) COMMIT_MS",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "repo_dir_sync.py",
"line": 57,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/serena/agent.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/serena/agent.py:1290`): 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/serena/agent.py"
},
"evidence": "g): p = subprocess.Popen( cmd, shell=True, c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/serena/agent.py",
"line": 1290,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/serena/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/serena/cli.py:112`): 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/serena/cli.py"
},
"evidence": "if editor: subprocess.run([editor, path], check=False, **run_kwargs) elif sys.platform.startswith(\"",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/serena/cli.py",
"line": 112,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/serena/dashboard.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/serena/dashboard.py:843`): 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/serena/dashboard.py"
},
"evidence": "try: p = subprocess.Popen( [sys.executable, \"-c\", f\"import webbrowser; webbrowser.open({u",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/serena/dashboard.py",
"line": 843,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/serena/util/shell.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/serena/util/shell.py:28`): 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/serena/util/shell.py"
},
"evidence": "getcwd() process = subprocess.Popen( command, shell=True, stdin=subprocess.DEVNULL,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/serena/util/shell.py",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/solidlsp/language_servers/common.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/solidlsp/language_servers/common.py:115`): 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/solidlsp/language_servers/common.py"
},
"evidence": "command, shell=True, check=False, cwd=cwd, capture_output=False,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/solidlsp/language_servers/common.py",
"line": 115,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/serena/agent.py)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/serena/agent.py:735`): 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.",
"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/serena/agent.py"
},
"evidence": "try: requests.get(\"https://oraios-software.de/serena_usage.php\", params=params, timeout=1) ex",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/serena/agent.py",
"line": 735,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (docs/create_toc.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`docs/create_toc.py:9`): 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": "docs/create_toc.py"
},
"evidence": ">{toc_file}\" print(cmd) os.system(cmd)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "docs/create_toc.py",
"line": 9,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/build_news_json.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/build_news_json.py:55`): 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": "scripts/build_news_json.py"
},
"evidence": ".json to Hades\" os.system(f\"scp news/news.json {user}@hades:/var/www/html/oraios-software/serena_news.json\")",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/build_news_json.py",
"line": 55,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/bump_version.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/bump_version.py:56`): 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": "scripts/bump_version.py"
},
"evidence": "eturn else: os.system(\"uv lock\") click.echo(f\"Bumped version to {new_version}\") os.system(\"g",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/bump_version.py",
"line": 56,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/live_test_grok.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/live_test_grok.py:145`): 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": "scripts/live_test_grok.py"
},
"evidence": "ry: completed = subprocess.run(argv, capture_output=True, text=True, timeout=timeout, cwd=cwd, env=env, input=st",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/live_test_grok.py",
"line": 145,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "746b3d85e4a8ac154b31b8dd3c2ab8865be8a7bbb49df0dc4a0c52e4b39a9994",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 6,
"medium": 1,
"low": 4,
"info": 0
}
}
}