update-docs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): The instructions are strictly focused on documentation workflows with no attempts to bypass safety filters or override system behavior.
- Data Exposure & Exfiltration (SAFE): No sensitive file access or network communication detected. The skill interacts only with repository code and documentation.
- Unverifiable Dependencies & Remote Code Execution (SAFE): Uses standard tools like git and pnpm for repository state and formatting checks. No external scripts are downloaded or executed.
- Indirect Prompt Injection (LOW): (1) Ingestion points: Reads source code files and .mdx documentation files. (2) Boundary markers: Absent. (3) Capability inventory: Uses git diff and pnpm lint; no arbitrary code execution or network exfiltration capabilities. (4) Sanitization: None detected, but the scope is limited to suggested edits for documentation.
Audit Metadata