ux-feedback
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by processing external inputs without defined safety boundaries.
- Ingestion points: The skill utilizes the
$ARGUMENTSvariable to specify the target and directs the agent to read from a local configuration file (DESIGN-LANGUAGE.md). - Boundary markers: The instructions lack specific delimiters or instructions for the agent to disregard potential instructions embedded within the target files or design documentation.
- Capability inventory: The skill is restricted to UI code generation; it does not exhibit high-risk capabilities such as network access, file system writes, or subprocess execution.
- Sanitization: No input validation or escaping mechanisms are prescribed for the ingested content.
Audit Metadata