pentest-api-deep

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

• Third-party content exposure detected (high risk: 1.00). The skill's toolset (e.g., kiterunner_scan, graphql_introspect, arjun_discover, graphql_cop, batchql, grpcurl_list/grpcurl_call) explicitly fetches and parses content from arbitrary target URLs and third‑party APIs (user-provided/open web endpoints), so the agent would read untrusted responses that could carry indirect prompt injection.