alterlab-hypothesis-gen
Warn
Audited by Snyk on Apr 12, 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.md "Conduct Comprehensive Literature Search" section explicitly instructs the agent to use WebFetch with PubMed URLs and general WebSearch to fetch and synthesize public web and PubMed content, which the agent is expected to read and use to drive hypothesis generation and experimental design, creating clear exposure to untrusted third‑party content that could alter actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata