project-wiki
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates locally within the project directory to manage documentation files and does not engage in any suspicious network or system operations.
- [PROMPT_INJECTION]: The skill instructions involve reading and analyzing existing project documentation (wiki files and CLAUDE.md). This presents a standard surface for indirect prompt injection, where malicious instructions embedded in the processed documentation could theoretically influence the agent. However, this interaction is fundamental to the documentation management task and does not show signs of malicious intent or bypass techniques.
- Ingestion points: Scans and reads files within the wiki/ directory and the CLAUDE.md file.
- Boundary markers: Absent; the skill relies on standard markdown structures and templates.
- Capability inventory: File system access (read/write), directory listing, and utility usage (grep, wc, git).
- Sanitization: Not present; the agent is expected to process and organize the text as-is.
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell utilities like grep for consistency checks and git mv for file archiving. These commands are used according to best practices for documentation maintenance and are restricted to the project's documentation scope.
Audit Metadata