auto-task
Warn
Audited by Snyk on May 14, 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 instructs the agent to use WebSearch/WebFetch and sub-agents to retrieve content from public/third-party sources (see "工具完全自由" in §3, "Step 2 · 执行" listing WebSearch/WebFetch, TASK.md tool suggestions, and §8 Sub-agent protocol), so untrusted web content will be ingested and can directly influence decisions and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata