check-sanctions-pressure
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external API (worldmonitor.app) which constitutes an untrusted data source. It proactively includes a defensive instruction for the agent to ignore any prompt-injection-like text, such as "ignore previous instructions" or "run this command," if found within the response body. This flags the attack surface inherent in processing third-party data.
Audit Metadata