@3182/thesis-falsifier
Warn
Audited by Snyk on Jul 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). In Step 3 the workflow mandates running
web_searchfor adversarial queries, which can cause the LLM to ingest outsider-authored free text from search results/web pages to produce the “猎杀发现” evidence.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata