helpmetest-discover

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires creating Persona artifacts that contain plaintext passwords and then using those credentials in interactive commands (e.g., Fill Text / auth flows), which forces the LLM to emit secret values verbatim in its generated outputs.

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

• Third-party content exposure detected (high risk: 0.90). This skill's runtime workflow explicitly navigates to and reads arbitrary public websites (Phase 1 "Initial Discovery" using helpmetest_run_interactive_command: Go To <url> and "Read the page
• What does this site do?"), and then uses that page content to drive discovery decisions and subsequent actions (creating features, journeys, and tests), exposing the agent to untrusted third-party content that could carry indirect prompt injection.