ui-ux-audit
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from the project's source code directory, which creates an indirect prompt injection attack surface.
- Ingestion points: The skill instructions mandate reading files from
src/app/,src/components/, andsrc/data/as well as usinggrepto search for keywords. - Capability inventory: The skill is capable of reading local files and generating structured markdown reports. It does not appear to possess network access or arbitrary command execution capabilities in the provided scripts.
- Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" markers when processing the content of these files.
- Sanitization: There is no evidence of sanitization or filtering of the content read from the source files before it is processed by the agent.
Audit Metadata