helpmetest-discover

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs creating Persona artifacts containing a plaintext "password" field (with a sample value "SecureTest123!"), which requires the LLM to emit secret/password values verbatim in its outputs.

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

• Third-party content exposure detected (high risk: 0.90). This skill's Phase 1 "Initial Discovery" explicitly directs the agent to navigate to and "Read the page" at arbitrary URLs using helpmetest_run_interactive_command (e.g., "Go To ...") so the agent fetches and interprets untrusted third‑party web content which can materially influence subsequent testing actions.