baseline-ui
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied file content during UI reviews, creating a surface for potential injection of instructions.
- Ingestion points: The
/baseline-ui <file>command allows the agent to read external file content (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed files.
- Capability inventory: The skill is purely informational and lacks capabilities such as network access, shell command execution, or file writing.
- Sanitization: No content filtering or validation is specified for the ingested file data.
Audit Metadata