frontend-design
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes design context by reading a local file named '.impeccable.md'. This represents a data ingestion surface where external instructions could be incorporated into the agent's context. The skill also offers to write to this file to store gathered context.
- Ingestion points: Reads '.impeccable.md' from the project root (SKILL.md).
- Boundary markers: Absent. The skill does not use specific delimiters or warnings to ignore embedded instructions within the context file.
- Capability inventory: The skill has the capability to write the gathered design context to '.impeccable.md' in the project root (SKILL.md).
- Sanitization: Absent. The skill does not describe any sanitization or validation of the content read from the context file.
Audit Metadata