12agent-novel
Warn
Audited by Snyk on Apr 19, 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's workflow (SKILL.md and VERSION-2.8.0.md, plus optimizations/early-style-research-parallel.md) explicitly starts a background "early-style-research" task that analyzes works from public platforms (晋江/长佩/起点/番茄) — i.e., ingesting user-generated, open-web content to produce style reports that feed the agent's decisions and style prompts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata