monitor-supply-chain-stress
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the worldmonitor.app API, which represents a potential surface for indirect prompt injection.
- Ingestion points: The GET request to worldmonitor.app/api/supply-chain/v1/get-shipping-stress defined in SKILL.md.
- Boundary markers: The skill includes a robust 'Content safety' section instructing the agent to treat responses as data only and to disregard any directive-like text.
- Capability inventory: The skill performs network requests using curl.
- Sanitization: The instructions provide specific guidance for the agent to treat symbols and names as non-executable content.
- [PROMPT_INJECTION]: A heuristic match for instruction override phrases was identified as a false positive, as the phrases appear within a defensive section designed to protect the agent from external data manipulation.
Audit Metadata