marketplace-rate-limiting
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements logic to ingest and process data from external VTEX APIs (e.g., catalog sync, order feed, and rate limit headers). This creates a surface where an attacker with control over VTEX API responses could attempt to inject malicious instructions. The skill provides code templates for handling this data but does not explicitly demonstrate input sanitization or boundary markers for the ingested content.
Audit Metadata