deep-research

Warn

Audited by Snyk on May 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill clearly ingests and interprets public third-party content as part of its required Phase 2 workflow—e.g., bibliography_agent's systematic search and Step 4.5 Semantic Scholar deduplication (and v3.9.0 triangulation calling Semantic Scholar / OpenAlex / Crossref) plus full-text screening and monitoring_agent's Retraction Watch / PubMed / Google Scholar alerts—which can materially influence synthesis, meta-analysis, and subsequent agent actions, creating a surface for indirect prompt injection.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

  • Hidden Unicode characters detected (1 type(s) found)

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W021
MEDIUM

Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 21, 2026, 05:53 PM
Issues
2
Security Audit — snyk — deep-research