hunt-information-disclosure

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This skill contains explicit, actionable reconnaissance steps for discovering and extracting sensitive data (config files, .env, .git, source maps, NEXT_PUBLIC keys), user enumeration and package/version harvesting—behaviors that directly enable credential theft, data exfiltration, and supply-chain attacks.

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

• Third-party content exposure detected (medium risk: 0.30). The workflow in SKILL.md has an outsider POST/GET supply malformed inputs (e.g., to /api/login and /api/users) and then “Check response for sensitive data” and stack traces, meaning attacker-controlled free text is directly ingested and reflected/processed by the target app at runtime.