skills/pdben-auto/design-patent-design-around-skill/design-patent-search-and-design-around/Gen Agent Trust Hub
design-patent-search-and-design-around
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data from marketplace URLs, product images, and patent databases. This configuration creates a vulnerability where malicious instructions embedded in web content could influence the agent's behavior. \n
- Ingestion points: Physical product briefs, marketplace URLs (
target_product), images (product_visuals), and external patent records. \n - Boundary markers: Absent. The instructions do not define delimiters or specific markers to isolate untrusted data from the agent's core instructions. \n
- Capability inventory: The skill requires web browsing and image analysis capabilities to fulfill its purpose. \n
- Sanitization: Absent. There are no instructions for technical sanitization or filtering of remote content during the data ingestion phase.
Audit Metadata