clerk-monorepo
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates agent interaction with a large codebase, creating an inherent ingestion surface for untrusted data.
- Ingestion points: Source code and documentation within the monorepo structure.
- Boundary markers: The skill establishes AGENTS.md as the authoritative rule set.
- Capability inventory: The agent is authorized to execute development commands (pnpm) and perform file writes (changesets).
- Sanitization: Relies on standard repository maintenance and PR review workflows.
- [EXTERNAL_DOWNLOADS]: The skill references standard development tool acquisition from well-known sources.
- Details: Recommends installing the 1Password CLI via Homebrew (brew) and managing project dependencies through pnpm.
Audit Metadata