compress-file
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and modify external instruction files, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill reads the entire content of a target instruction file (SKILL.md) to identify structural overlaps.
- Boundary markers: The instructions do not define delimiters or provide specific 'ignore' directives to prevent the agent from following instructions embedded within the processed file.
- Capability inventory: The skill uses the 'Edit' tool to perform filesystem modifications and invokes the 'tighten-instruction' skill to process text.
- Sanitization: No sanitization, validation, or filtering of the target file content is performed prior to the analysis and editing steps.
Audit Metadata