cn-thesis-research-design
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow ingests the outsider-authored user request to detect routing axis values (e.g., in SKILL.md step 3-4), then selects mapped fragments and runs the core workflow, so free text directly influences the LLM runtime processing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata