design-bridge
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external DESIGN.md files, which poses a risk of indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The skill is instructed to fetch design documents from the "awesome-design-md" collection or local cache (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or to ignore potential instructions embedded within the source design documents.
- Capability inventory: The skill possesses workspace-write capabilities, allowing it to generate and save instruction files based on the input data (SKILL.md).
- Sanitization: No mechanisms for sanitizing or validating the content of the external design documents are specified before the data is processed and written to the workspace.
Audit Metadata