impl-validator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review untrusted data in the form of artifacts and implementation goals.
- Ingestion points: Data enters through the structured
check:block or user input described in SKILL.md. - Boundary markers: Employs a specific input block format as a delimiter.
- Capability inventory: The skill uses file-read capabilities for inspection but lacks the ability to write files or access the network.
- Sanitization: The instructions do not specify any validation or sanitization for the content of the artifacts being inspected.
Audit Metadata