catalog-listings
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and act upon data from external sources, which represents a potential entry point for unintended instructions.
- Ingestion points: The skill retrieves review snippets using the
get_listingtool and accepts pasted spec sheets or notes as source material inSKILL.md. - Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for these inputs.
- Capability inventory: The skill has the ability to stage updates to the catalog using the
stage_listing_updatetool. - Sanitization: The instructions do not describe specific sanitization or filtering logic for the ingested content.
Audit Metadata