bug-bounty

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

• Third-party content exposure detected (high risk: 0.90). The skill's agents (e.g., recon-agent and recon pipeline in SKILL.md) explicitly crawl and fetch public third‑party content (waybackurls, gau, katana, JS files, GitHub dorks, HackerOne GraphQL queries) and the autopilot/recon-ranker/chain-builder agents are instructed to read and act on those results to choose tests and follow-up actions, creating a clear path for untrusted web content to influence agent behavior.