check-forecast-signals

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill text includes a literal API key string (wm_0123456789abcdef0123456789abcdef01234567) and instructs callers to present an API key in the X-WorldMonitor-Key header, which encourages embedding secret values verbatim in requests or generated outputs.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md describes calling the runtime endpoint GET /api/forecast/v1/get-forecasts, whose JSON fields like signals[].value, scenario, and title are untrusted upstream text that will be ingested into the agent’s LLM context as free-form content.

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

• Secret detected (high risk: 1.00). The string "wm_0123456789abcdef0123456789abcdef01234567" is a high-entropy, literal API-key–formatted value (prefix "wm_" + long hex-like token) and is directly present in the docs rather than a generic placeholder like "YOUR_API_KEY" or "sk-xxxx". It therefore meets the definition of a secret that could be a usable credential and is flagged.