baseline-ui
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows for the analysis of user-provided code files via the
/baseline-ui <file>command, which creates a potential surface for indirect prompt injection attacks where malicious instructions hidden in the analyzed files could influence the agent's behavior.\n - Ingestion points: Source code files processed at runtime via the file review command in
SKILL.md.\n - Boundary markers: The instructions do not define delimiters or provide specific guidance for the agent to ignore instructions embedded within the processed content.\n
- Capability inventory: The skill logic is limited to text-based output, specifically quoting code violations and suggesting fixes. It does not invoke subprocesses, perform file writing, or initiate network requests.\n
- Sanitization: The skill lacks mechanisms to sanitize or filter the content of external files before processing.
Audit Metadata