citation-verifier

Warn

Audited by Snyk on Feb 16, 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 performs WebFetch/WebSearch and API lookups against public sites (CrossRef, arXiv.org, pubmed.ncbi.nlm.nih.gov, openlibrary.org, and arbitrary academic URLs) and is expected to read and interpret those fetched third-party pages/metadata, exposing the agent to untrusted public content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:18 AM