monitor-health-alerts
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains the phrase "ignore previous instructions" within its "Content safety" section. This is a defensive instruction advising the agent to disregard potential prompt injection attempts that might be present in external data responses, rather than an attempt to bypass agent safety filters.
- [CREDENTIALS_UNSAFE]: A documentation-only API key placeholder
wm_0123456789abcdef0123456789abcdef01234567is included in the authentication examples. This is not a functional credential. - [EXTERNAL_DOWNLOADS]: The skill is configured to fetch data from
api.worldmonitor.app. This network communication is essential for the skill's primary function of providing real-time health and environmental alerts.
Audit Metadata