docyrus-cli-app

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt includes examples that pass secrets directly on the command line or in explicit Authorization headers (e.g., --accessToken "", --headers '{"Authorization":"Bearer "}'), which would require the LLM to emit secret values verbatim when generating runnable commands or guidance.

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

• Third-party content exposure detected (high risk: 0.80). The skill's documented workflows (e.g., "docyrus discover connector-curl" and the "action" command in SKILL.md / references/cli-manifest.md) explicitly send requests to external providers such as Meta WhatsApp and ingest their responses, meaning the agent will fetch and interpret untrusted, user-generated third‑party content that can influence subsequent actions.