scientific-literature-search

Warn

Audited by Snyk on Jul 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime workflow where Tier 2 uses an AI web search tool (Claude web_search_20250305) and Tier 3 fetches/extracts full text from arbitrary URLs/PDFs (e.g., trafilatura.fetch_url / pypdf), which would ingest outsider-authored free text from public web pages and papers into the LLM context.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 03:36 PM
Issues
1
Security Audit — snyk — scientific-literature-search