flux-opencode-contribute

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

• Third-party content exposure detected (low risk: 0.10). In SKILL.md the runtime workflow takes the user-supplied “Issue description” from $ARGUMENTS and later interpolates it into the GitHub PR body ($ISSUE_DESCRIPTION), but it does not describe the agent ingesting outsider-authored free text from any external monitored/readable feed or arbitrary content source.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill runs "gh repo clone Nairon-AI/flux-opencode" at runtime and then invokes repository scripts (e.g., ./scripts/smoke-test.sh), so the cloned repo Nairon-AI/flux-opencode is fetched and its code would be executed at runtime, directly controlling behavior.