specrail-workflow

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

• Third-party content exposure detected (high risk: 0.70). High likelihood because the required startup flow can read GitHub issue/PR “evidence” from an outsider-authored issue body via checks/github_issue_evidence.py ... --json > issue-evidence.json, whose resulting free-form text would then be ingested by downstream route/focused skills when they use that evidence.