triaging-issues
Warn
Audited by Snyk on Jul 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The workflow fetches GitHub issue title/body/comments (outsider-authored free text) via
bash scripts/get_issue.shandbash scripts/get_comments.shand then uses that text for categorization and to writecomment_params.summary(even though it must not echo it verbatim), so untrusted prose enters the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata