update-dedupe
Warn
Audited by Snyk on Jun 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The runtime LLM context is fed by the runner-provided “aggregated duplicate feedback JSON” derived from GitHub issue timeline data (outsider-authored issue titles/bodies/timeline text) that the skill reads in step 1, so it can include outsider free text for summarization.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata