issue-driven-development
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to "Read all comments on the issue" (GitHub issue comments are user-generated) and to perform online research including Stack Overflow and other web resources, meaning it ingests untrusted third-party content as part of its workflow.
Audit Metadata