context-compressor
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines procedures for summarizing external code and configuration files, creating a surface where malicious instructions embedded in those files could influence agent behavior.
- Ingestion points: The skill instructions involve processing arbitrary source files (e.g., src/auth/login.ts, src/config.ts) provided to the agent.
- Boundary markers: The skill uses Markdown templates and headers for organizational structure, but does not provide explicit isolation or instructions to disregard potential commands found within the ingested data.
- Capability inventory: The skill is designed to work with file-reading capabilities, specifically referencing the context-fetch tool.
- Sanitization: There are no defined mechanisms for sanitizing or escaping the content of processed files before they are summarized.
Audit Metadata