scienceclaw-retrieval

Warn

Audited by Snyk on Apr 6, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly directs the agent to query and ingest results from public third‑party databases (PubMed, arXiv, Semantic Scholar, CrossRef, OpenAlex) and to perform citation chaining and relevance re‑ranking on those results, meaning untrusted external content is read and can materially influence follow‑up searches and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 6, 2026, 11:31 PM
Issues
1
Security Audit — snyk — scienceclaw-retrieval