academic-verify
Warn
Audited by Snyk on May 13, 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 routes claim lookups through perplexity-research (Step 3: "Invoke perplexity-research with citation-mode") and lists public/untrusted sources (Retraction Watch, PubPeer, OSF, etc.), meaning the agent fetches and ingests third‑party web content that is then used to form verdicts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata