technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
pnpm --filter @repo/docu checktypesto validate documentation changes. This is a standard development workflow command used for type-checking in Node.js/TypeScript monorepos. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from a variety of repository sources including
AGENTS.md, source code, tests, CLI help, and existing markdown files. - Ingestion points: The skill reads repository files, architecture documents, issues, and user reports to gather technical information.
- Boundary markers: No specific delimiters or boundary markers are defined in the instructions to separate external data from the agent's internal reasoning.
- Capability inventory: The skill allows for local command execution (
pnpm) and file system reads/writes to documentation paths. - Sanitization: The skill relies on a verification hierarchy (Source > Tests > CLI help) to ensure accuracy and instructions are provided to omit claims that cannot be verified.
Audit Metadata