recon-scope-triage

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

• Third-party content exposure detected (high risk: 0.70). This skill’s runtime workflow ingests the operator-supplied “ASM report/recon export/breach combo/repo list/bucket list/mobile-app list” (outsider-authored free text could be embedded in those feeds), then uses it as input for LLM reasoning/triage; SKILL.md itself doesn’t show hard sandboxing or explicit stripping of untrusted text.