industrial-ai-research

Warn

Audited by Snyk on Mar 14, 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 mandatory Source Collection and Source Strategy explicitly require fetching and reading open/public third-party sources (e.g., arXiv recent listings, IEEE Xplore and publisher/conference pages) and SURVEY_EVIDENCE.md requires extracting verbatim snippets and anchor facts from those papers, so untrusted web content is ingested and directly drives synthesis and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 08:57 AM
Issues
1