skill-prune
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from various files in the repository to identify candidates for deletion.
- Ingestion points: Reads content from SKILL.md files, reference files, and engagement logs (attack-chain.md).
- Boundary markers: None identified for distinguishing between data and instructions during processing.
- Capability inventory: The skill proposes and executes file deletions via tool calls.
- Sanitization: No specific sanitization or validation of the processed file content is described.
- [COMMAND_EXECUTION]: The skill procedure involves executing a local repository maintenance script.
- Evidence: 'Run scripts/skill_linter.py --check-orphans' in the Procedure section.
Audit Metadata