docs
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands including
rg(ripgrep) for searching the codebase and documentation,git diff --checkfor whitespace validation, andpnpm run buildfor website construction. These are standard utility commands for a development environment. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads and processes content from the local file system to validate documentation state.
- Ingestion points: Contents of
website/docs,docs,pkg,cmd, andinternaldirectories are searched using thergtool. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are defined for the ingested data.
- Capability inventory: Includes local file reading via
rg, build execution viapnpm, and project validation viagit. - Sanitization: No explicit sanitization or filtering of the ingested file content is defined.
Audit Metadata