flux-opencode-scope

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md describes that the required workflow captures the user-provided “Full request” (feature/bug description or a file path) and then uses that untrusted text as the basis for research/scoping; this is outsider-authored free text ingested at runtime via the argument input.