pentest-validation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly sends payloads to and inspects responses from a user-supplied target_url (e.g., SKILL.md config target_url and the Tier‑2/Tier‑3 validation pipelines and test cases like tc004/tc005 referencing https://staging.example.com and the Task("Exploit Validation", { target_url: ... }) orchestration), so it fetches and interprets untrusted third‑party web content to decide exploit success and drive subsequent actions.