swe-bench
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly targets solving "GitHub Issue" and its required Phase 1 workflow ("阅读 Issue") instructs the agent to read and act on user-reported issue content (SKILL.md), which is untrusted, user-generated third‑party content that can materially influence reproduction, testing, and code-change decisions.
Audit Metadata