permission-analyzer
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill executes a local Python script located at
~/.claude/skills/permission-analyzer/scripts/analyze_permissions.py. This is the intended primary function of the skill to perform its analysis. - INDIRECT_PROMPT_INJECTION (LOW): The skill processes session logs which may contain untrusted data from previous external interactions.
- Ingestion points: Session logs containing historical Bash commands and tool outputs.
- Boundary markers: None explicitly defined in the provided markdown.
- Capability inventory: The skill has the capability to modify
.claude/settings.json, effectively changing the agent's security posture. - Sanitization: The skill documentation specifies a 'Deny list' that explicitly filters out destructive commands (e.g., sudo, rm -rf) and sensitive file patterns (e.g., .env, .pem).
Audit Metadata