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
Risk Level
SAFE
Analyzed
Feb 18, 2026, 01:33 PM