ClawHub
Back to skill

Security audit

VideoLens

Security checks for vulnerabilities and agentic risk

Overview

The skill is transparent about its purpose, but it downloads and runs external code that receives the user's OpenAI key and video content without sandbox or signature verification.

Install only if you are comfortable allowing a pinned external VideoLens runtime to process selected videos with your OpenAI key. Use a dedicated low-budget OpenAI key, avoid sensitive videos unless you accept transmission to OpenAI, and remove the managed VideoLens state directory if you no longer want cached media artifacts and reports retained locally.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
skill.py:17
Finding

Externally Retrieved Runtime Executes with API Credentials and User-Selected Media Access

Content
View full analysis
dict[str, str]: env = _sanitized_base_env() api_key = os.environ.get("OPENAI_API_KEY", "").strip() if api_key: env["OPENAI_API_KEY"] = api_key env["VIDEOLENS_CACHE_DIR"] = str(_state_root() / "cache" / "videolens") env["PYTHONPATH"] = str(_repo_dir() / "src") return env ``` ```python result = _run_command( _build_analyze_command(spec, output_dir), env=_analysis_env(), cwd=repo_dir, timeout=_bounded_int( spec.get("command_timeout_seconds"), default=1800, mi ...[truncated 3421 chars]
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (7)

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_read' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'file_write' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'network' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'shell' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · skill.py (reported line 231)May include surrounding context.

python
timeout: int = 300,
) -> dict[str, Any]:
    try:
        completed = subprocess.run(
            command,
            cwd=str(cwd) if cwd else None,
            env=env if env is not None else _sanitized_base_env(),

Tainted flow: 'env' from os.environ.get (line 178, credential/environment) → subprocess.run (code execution)

Medium
Category
Data Flow
Confidence
65% confidence
Finding

Data from a source is assigned to a variable that is later passed to a sink, creating a variable-mediated taint flow.

Content

Scanner excerpt · skill.py (reported line 231)May include surrounding context.

python
timeout: int = 300,
) -> dict[str, Any]:
    try:
        completed = subprocess.run(
            command,
            cwd=str(cwd) if cwd else None,
            env=env if env is not None else _sanitized_base_env(),

Static analysis

No suspicious patterns detected.