prune-context-file
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill performs local file system operations (read and write) on repository context files. This is the core functionality of the skill and is performed within the user's project environment.
- [PROMPT_INJECTION]: The skill processes external repository context files which constitutes an indirect prompt injection surface. Ingestion points: reads CLAUDE.md or AGENTS.md in SKILL.md. Boundary markers: none specified to separate data from instructions. Capability inventory: performs file reads and file writes. Sanitization: no explicit sanitization or filtering of the ingested content is mentioned. The risk is mitigated by the skill's narrow operational scope and requirement for user approval before modifying files.
Audit Metadata