refine-task

Warn

Audited by Snyk on Aug 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). In the required runtime workflow, the skill ingests outsider-authored free text from the specified Jira/GitHub work item via ITEM_URL/ITEM_CONTEXT (and possibly fetched tracker content), then dispatches it to the refinement-reviewer subagent for analysis and comment drafting.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 07:21 PM
Issues
1
Security Audit — snyk — refine-task