init-latex-project

Warn

Audited by Snyk on May 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill's init.sh and sources.yaml explicitly auto-download official style packages from public third-party sites (e.g., icml.cc, neurips.cc, GitHub repos, CVF/media.eventhosts.cc) as part of the required setup, and SKILL.md also directs the agent to rely on external Overleaf compile logs/previews — meaning untrusted public content is fetched/ingested and can influence compilation and subsequent agent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 5, 2026, 12:39 PM
Issues
1