monitor-health-alerts

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes a literal API key value (wm_0123456789abcdef0123456789abcdef01234567) and instructs use of the X-WorldMonitor-Key header, which can cause the LLM to embed or reproduce the secret verbatim in generated commands or code, posing a high exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required workflow calls public health service endpoints and ingests their JSON response fields (e.g., summaries, source names, source URLs) into the agent’s LLM context, which is outsider-authored free text/data at runtime.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The file contains a literal, high-entropy API key in an example header: "X-WorldMonitor-Key: wm_0123456789abcdef0123456789abcdef01234567". This is not a placeholder (it is a concrete key-like value with a wm_ prefix and long hex-like characters), so it qualifies as a secret.