purchase-advisor
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from web searches and product listings.
- Ingestion points: The skill fetches product listings, retailer pages, consumer reviews, and product manuals from the internet (SKILL.md, sections 4 and 5). It also downloads and processes images from second-hand marketplaces.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the fetched content.
- Capability inventory: The agent can perform web searches, fetch arbitrary URLs, process images (vision), and write data to the effort-store skill (SKILL.md, sections 2, 4, 5, and 6).
- Sanitization: Absent. No explicit sanitization or filtering of the fetched content is required before processing or inclusion in the shortlist/recommendation.
Audit Metadata