check-forecast-signals
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: Static analysis flagged the phrase 'ignore previous instructions', but this occurs within a safety guideline. The skill explicitly warns the agent to ignore any directive-like text or commands found inside the API data, serving as a defense against indirect prompt injection.
- [EXTERNAL_DOWNLOADS]: The skill performs legitimate network requests to 'api.worldmonitor.app' to fetch data. This behavior is documented and corresponds to the skill's primary function.
- [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were detected. The skill uses standard API authentication headers and targets the developer's infrastructure.
Audit Metadata