skills/simota/agent-skills/prune/Gen Agent Trust Hub

prune

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies and audits other skills by reading their instructions, capabilities, and associated journals, creating a surface for potential instruction injection from the audited data.\n
  • Ingestion points: The skill reads SKILL.md files, ~/.claude/profiles/*.json configurations, .agents/*.md journals, and PROJECT.md activity logs (documented in SKILL.md and reference/retention-criteria.md).\n
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are mentioned for the content being scanned.\n
  • Capability inventory: The skill is strictly 'propose-only' and cannot modify or delete files. It delegates merge operations to the 'Architect' skill and requires manual user approval for any skill removals.\n
  • Sanitization: The skill lacks explicit sanitization routines but utilizes a quantitative 5-axis scoring system (usage, overlap, uniqueness, coverage, maintenance) which relies on objective metadata rather than just processed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:03 PM