ai-director

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to ask the user for an API key and then pass it as a direct command-line argument to a verification script (node scripts/ad-account-manager.js verify-key x2c_sk_xxx), which exposes the secret value through the LLM's context and output.

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

• Third-party content exposure detected (low risk: 0.10). The quality-evaluator script ingests external video URLs and passes them to the Gemini API, representing low-risk ingestion of arbitrary/user-supplied URLs.