detecting-aws-credential-exposure-with-trufflehog

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md and scripts/agent.py explicitly run TruffleHog against public GitHub organizations/repositories and other third‑party locations (e.g., "trufflehog github --org", "trufflehog git https://github.com/...", S3 scans), so the agent ingests untrusted, user-generated content from the open web and uses those findings to drive actions like checking or deactivating AWS keys.