detecting-secrets

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly includes a "GitHub Secret Scanning Integration" with gh api calls (e.g., gh api /repos/{owner}/{repo}/secret-scanning/alerts) that fetch user-generated alerts from GitHub repos, which the agent would read and use to drive remediation decisions, exposing it to untrusted third‑party content that could carry indirect prompt injection.