retail-assortment-gap-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and analyzes product information (titles, descriptions, and category paths) from external retailers like Shopify, Target, and IKEA via the Crawlora API. This untrusted content serves as a surface for indirect prompt injection.
- Ingestion points: JSON payloads returned by
scripts/crawlora.shwhich are then processed by the agent to perform gap analysis. - Boundary markers: The instructions in
SKILL.mddo not specify the use of delimiters or provide "ignore embedded instructions" warnings for the retail data being ingested. - Capability inventory: The agent has access to
scripts/crawlora.sh, which performs network operations (GET and POST requests viacurl) using an API key. - Sanitization: Although
scripts/crawlora.shimplements defensive coding (including path whitelisting, shell argument sanitization, and preventingcurlfrom reading local files via the@prefix), the skill does not define sanitization or validation logic for the content returned by the external retail catalogs before the agent processes it.
Audit Metadata