totp-secret-store

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

• Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the skill can invoke scripts/scan_leaks.py --protect .local --all, which reads outsider-authored free text from the user-provided repository files (tracked and optionally untracked non-ignored) at runtime via path.read_text() and scans their contents with regexes.