documentation
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-provided Markdown files, creating a surface for indirect prompt injection.
- Ingestion points: Documentation files are analyzed in sub-skills/maintain.md, sub-skills/initialize.md, and sub-skills/compress.md using shell tools.
- Boundary markers: Absence of explicit markers or instructions to isolate document content during analysis.
- Capability inventory: Includes file read/write access and the execution of shell analysis tools like grep and wc.
- Sanitization: No sanitization is applied to the content read from the Markdown files.
- [COMMAND_EXECUTION]: Employs standard Unix utilities for auditing the repository structure and document content.
- Evidence: Utilizes find, grep, ls, and wc within the maintenance and initialization sub-skills to discover files and measure documentation length.
Audit Metadata