product-information-management
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through the ingestion of external product data.
- Ingestion points: Data is fetched from remote PIM systems (Akeneo, Salsify) via REST APIs and processed through webhook endpoints (
POST /api/webhooks/akeneoinSKILL.md). - Boundary markers: None identified. The code snippets in
SKILL.mdmap API fields directly to internal data structures without using delimiters or instructions to ignore embedded content. - Capability inventory: The integrated scripts perform database updates (
db.products.upsert), network operations viafetch, and CDN cache invalidation (revalidateProductPage). - Sanitization: There is no evidence of HTML escaping or instruction filtering for the product descriptions and metadata before they are stored or published to the storefront.
Audit Metadata