Claude Code Telegrammer — 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": "claude-code-telegrammer",
"source": {
"kind": "package",
"origin": "claude-code-telegrammer"
},
"server": {
"name": "claude-code-telegrammer"
}
},
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"tags": [
"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 (11 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/skills/skill-creator/eval-viewer/generate_review.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`.claude/skills/skill-creator/eval-viewer/generate_review.py:291`): 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/skills/skill-creator/eval-viewer/generate_review.py"
},
"evidence": "try: result = subprocess.run( [\"lsof\", \"-ti\", f\":{port}\"], capture_output=True, text=T",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/skill-creator/eval-viewer/generate_review.py",
"line": 291,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (docs/to_claude/examples/example-python-project-scitex/scripts/mnist/clf_svm.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`docs/to_claude/examples/example-python-project-scitex/scripts/mnist/clf_svm.py:73`): 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.",
"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/to_claude/examples/example-python-project-scitex/scripts/mnist/clf_svm.py"
},
"evidence": "scitex.io.save(model, eval(CONFIG.PATH.MNIST.MODEL_SVM)) return 0 def parse_args() -> argparse.Namespace: pa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "docs/to_claude/examples/example-python-project-scitex/scripts/mnist/clf_svm.py",
"line": 73,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in packaging/dev tooling (docs/to_claude/examples/example-python-project-scitex/scripts/mnist/download.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`docs/to_claude/examples/example-python-project-scitex/scripts/mnist/download.py:41`): 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.",
"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/to_claude/examples/example-python-project-scitex/scripts/mnist/download.py"
},
"evidence": "malize( eval(CONFIG.MNIST.NORMALIZE.MEAN), eval(CONFIG.MNIST.NORMALIZE.STD),",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "docs/to_claude/examples/example-python-project-scitex/scripts/mnist/download.py",
"line": 41,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/pptx/scripts/office/soffice.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/pptx/scripts/office/soffice.py: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.",
"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/skills/pptx/scripts/office/soffice.py"
},
"evidence": "= get_soffice_env() subprocess.run([\"soffice\", ...], env=env) \"\"\" import os import socket import subprocess import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/pptx/scripts/office/soffice.py",
"line": 14,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/pptx/scripts/office/validators/redlining.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/pptx/scripts/office/validators/redlining.py:138`): 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/skills/pptx/scripts/office/validators/redlining.py"
},
"evidence": "result = subprocess.run( [ \"git\", \"di",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/pptx/scripts/office/validators/redlining.py",
"line": 138,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/pptx/scripts/thumbnail.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/pptx/scripts/thumbnail.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": ".claude/skills/pptx/scripts/thumbnail.py"
},
"evidence": "tem}.pdf\" result = subprocess.run( [ \"soffice\", \"--headless\", \"--conver",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/pptx/scripts/thumbnail.py",
"line": 161,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/skill-creator/scripts/improve_description.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/skill-creator/scripts/improve_description.py:35`): 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/skills/skill-creator/scripts/improve_description.py"
},
"evidence": "UDECODE\"} result = subprocess.run( cmd, input=prompt, capture_output=True, text=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/skill-creator/scripts/improve_description.py",
"line": 35,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/skill-creator/scripts/run_eval.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/skill-creator/scripts/run_eval.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": ".claude/skills/skill-creator/scripts/run_eval.py"
},
"evidence": "DE\"} process = subprocess.Popen( cmd, stdout=subprocess.PIPE, stderr=subpro",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/skill-creator/scripts/run_eval.py",
"line": 85,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/webapp-testing/scripts/with_server.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/webapp-testing/scripts/with_server.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/skills/webapp-testing/scripts/with_server.py"
},
"evidence": "& process = subprocess.Popen( server['cmd'], shell=True, std",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/webapp-testing/scripts/with_server.py",
"line": 69,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/xlsx/scripts/office/soffice.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/xlsx/scripts/office/soffice.py: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.",
"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/skills/xlsx/scripts/office/soffice.py"
},
"evidence": "= get_soffice_env() subprocess.run([\"soffice\", ...], env=env) \"\"\" import os import socket import subprocess import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/xlsx/scripts/office/soffice.py",
"line": 14,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/xlsx/scripts/office/validators/redlining.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/xlsx/scripts/office/validators/redlining.py:138`): 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/skills/xlsx/scripts/office/validators/redlining.py"
},
"evidence": "result = subprocess.run( [ \"git\", \"di",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/xlsx/scripts/office/validators/redlining.py",
"line": 138,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (.claude/skills/xlsx/scripts/recalc.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`.claude/skills/xlsx/scripts/recalc.py:34`): 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/skills/xlsx/scripts/recalc.py"
},
"evidence": "out(): try: subprocess.run( [\"gtimeout\", \"--version\"], capture_output=True, timeout=1, check=Fal",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": ".claude/skills/xlsx/scripts/recalc.py",
"line": 34,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"claude-code-telegrammer\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "claude-code-telegrammer"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "reply",
"tags": [],
"reasons": {}
},
{
"tool": "react",
"tags": [],
"reasons": {}
},
{
"tool": "edit_message",
"tags": [],
"reasons": {}
},
{
"tool": "get_history",
"tags": [],
"reasons": {}
},
{
"tool": "get_unread",
"tags": [],
"reasons": {}
},
{
"tool": "mark_read",
"tags": [],
"reasons": {}
},
{
"tool": "download_attachment",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "send_document",
"tags": [],
"reasons": {}
},
{
"tool": "search_messages",
"tags": [],
"reasons": {}
},
{
"tool": "health",
"tags": [],
"reasons": {}
},
{
"tool": "get_context",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "56fe1f74c4b50bad7b4d6ce5577f27b9c0e7342c785f4630f01220e5c83ca2c3",
"stats": {
"tools": 11,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 0,
"low": 11,
"info": 1
}
}
}