triaging-issues
Warn
Audited by Snyk on Jun 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow ingests the GitHub issue’s title/body and comments via read-only scripts (
scripts/get_issue.shandscripts/get_comments.sh), which are outsider-authored free text from non-operating users, and that text is then used to generate the LLM context/decision.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata