monorepo
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted configuration files and metadata from external repositories, which can serve as a vector for malicious instructions.\n
- Ingestion points: The skill reads project instructions, manifests, repository state, and CI workflow configurations as specified in Section 1 of
SKILL.md.\n - Boundary markers: The instructions do not define specific delimiters for untrusted data, though they suggest using isolated copies and dry-run modes to minimize risk.\n
- Capability inventory: The skill has authority to install dependencies, execute build tasks, migrate tooling, and publish packages, which represents a high-impact capability set.\n
- Sanitization: The skill incorporates safety mitigations such as using pinned toolchains, locked installation modes, and manual review of lifecycle scripts before execution.
Audit Metadata