frontend-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code provided by the user, which could contain malicious instructions intended to manipulate the agent's review or behavior. \n
- Ingestion points: User-supplied frontend code and diffs from
web/andpackages/dify-ui/(defined in SKILL.md). \n - Boundary markers: Absent. The instructions do not define specific delimiters or "ignore" instructions for the content of the code being reviewed. \n
- Capability inventory: None. The skill defines a text-based review workflow and references documentation; it does not include instructions to execute shell commands or perform network requests based on the code's content. \n
- Sanitization: Absent. No sanitization or escaping of the ingested code is specified. \n- [EXTERNAL_DOWNLOADS]: The skill references UI guidelines hosted on Vercel Labs' official GitHub repository. \n
- Evidence:
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.mdinreferences/accessibility-ui.md.
Audit Metadata