free-keys

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill asks users to paste API keys, reads keys from env/shell, and instructs generating/verifying curl commands and Authorization headers and writing keys into env files — actions that require the LLM to handle and emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 6 "discover" step explicitly instructs the agent to perform web searches (e.g., search for "free LLM API keys" and a GitHub list) and report details from discovered public sites, meaning the agent will fetch and interpret untrusted third‑party web content which can change provisioning decisions and trigger follow-on actions (Phases 2–4).