assess-energy-shock

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires callers to present an API key in the X-WorldMonitor-Key header and even includes a literal example key, which forces the agent to handle or output secret values verbatim (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow is a server-side API call (GET /api/intelligence/v1/compute-energy-shock) that returns an assessment string and limitations derived from upstream datasets; since those upstream sources are not authored by the operating user, this can include outsider-authored free text that the agent would ingest from the API response into the LLM context.

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

• Secret detected (high risk: 1.00). The file contains a literal-looking API key in the example header: "wm_0123456789abcdef0123456789abcdef01234567". This is a high-entropy, prefixed token (not a generic placeholder like YOUR_API_KEY or sk-xxxx) and appears to be a real API key value embedded in the docs, so it should be treated as a secret. The other occurrences (e.g., use of $WM_API_KEY in the curl example) are environment variable references and are not secret values themselves.