to-issues

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

• Third-party content exposure detected (high risk: 0.80). The skill's "Gather context" step explicitly instructs the agent to "fetch [an issue] from the issue tracker and read its full body and comments," meaning it ingests user-generated issue-tracker content (potentially public/untrusted) that can materially influence subsequent decisions and tool use.