skill-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted third-party skill packages, including prompts and scripts, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent reads the target skill directory and all referenced files for package-level analysis as defined in SKILL.md and the prompt contract.
- Boundary markers: The skill contains explicit instructions in SKILL.md and prompts/skill-quality-review.md defining its scope as a 'static package review' and prohibiting the execution of business tasks or silent modification of files.
- Capability inventory: The skill is designed for read-only static analysis and reporting; it is not granted capabilities to execute the code it reviews or perform network operations based on reviewed content.
- Sanitization: The instructions mandate the separation of static findings from runtime evidence, requiring the agent to mark unverified claims as UNASSESSED or INSUFFICIENT_EVIDENCE.
Audit Metadata