ln-91-engineering-baseline-builder
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted repository content, such as manifests, lockfiles, and documentation, to generate project-specific guidance and local procedures.
- Ingestion points: Reads project type, runtimes, versions, manifests, lockfiles, and existing documentation from the repository (SKILL.md).
- Boundary markers: Explicitly instructs the agent to exclude secrets and volatile inventories and requires outcome-based evidence ('PROVEN') for all claims.
- Capability inventory: Authorized to use project-native editors and runtime tooling, and can create new local skills or procedures with commands derived from the project environment.
- Sanitization: Focuses on verification against official specifications and documentation, but does not specify technical sanitization or escaping of external content before processing.
Audit Metadata