task-executor
Warn
Audited by Snyk on Jul 15, 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). SKILL.md Step 1 loads outsider-authored ticket text via
getWorkItem(ticket-id)(e.g., JIRA/Linear/ADO issue description/acceptance criteria or local markdown work-item files), which is then embedded into the delegation prompt sent to the agent LLM in Step 4.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata