faceless-explainer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to detect, ask for, and accept API keys from the user and write them verbatim into PROJECT_DIR/.env (or echo detected keys), which requires the LLM to handle secret values directly and thus poses exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.95). Required runtime path: Step 1 writes the user’s arbitrary input text into capture/extracted/visible-text.txt, and Step 2 dispatches the scriptwriting subagent with Input text: ./capture/extracted/visible-text.txt (outsider-authored free text) as part of the LLM prompt context.