design-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for reviewing external content which introduces a surface for indirect prompt injection.
- Ingestion points: In
REVIEWmode, the skill instructs the agent to navigate to "Live URLs" or analyze "Code/snippets" provided by the user (found inSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or clear "ignore embedded instructions" warnings when processing the fetched content.
- Capability inventory: The agent uses navigation and analysis capabilities to process untrusted external data according to the 12-category rubric.
- Sanitization: There is no mention of sanitizing or filtering instructions that might be embedded within the HTML or code snippets being reviewed.
Audit Metadata