ux-friction-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided UI designs, HTML, and journey maps, which creates a potential surface for instructions embedded within that data to influence the agent.
- Ingestion points: Processes interface designs, user paths, and HTML snippets provided by the user for audit (SKILL.md).
- Boundary markers: The skill lacks explicit delimiters or instructions to treat provided UX data as non-executable text, which could lead to accidental obedience of embedded commands.
- Capability inventory: The skill is granted
Read,Write,Edit, andWebFetchpermissions (SKILL.md frontmatter). - Sanitization: There are no defined mechanisms for sanitizing or filtering instructions that might be present in the user-provided design documentation.
Audit Metadata