anti-ui-slop-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external repository data, including product briefs, component files, and visual screenshots. This establishes an attack surface where malicious instructions could be embedded in the code or documentation being reviewed. However, the skill lacks the capabilities (such as network access or file-write permissions) to act on such injections in a harmful way.
- Ingestion points: Repository documents, route/component files, and screenshots in SKILL.md.
- Boundary markers: Not explicitly defined in the prompt.
- Capability inventory: The skill is restricted to review tasks; no tool usage for network or file system modification is present.
- Sanitization: None identified for processing external content.
Audit Metadata