research-wiki

Warn

Audited by Snyk on Apr 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: 0.80). The skill's /research-wiki ingest step explicitly fetches and scans content from public third-party sources (arXiv/DBLP/Semantic Scholar) and uses that extracted content to create pages, add edges, rebuild query_pack, and drive downstream ideation, so external webpage/content can materially influence agent decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 09:07 AM
Issues
1