secrets-scanner

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs scanning and ingesting content from public/untrusted sources (e.g., "trufflehog github --org=", gitleaks detect --source ., and non-git sources like S3, public website assets and backups) so the agent would read and act on third‑party/user‑generated content that can influence remediation decisions.