citation-verifier

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: 0.70). The script (.codex/skills/citation-verifier/scripts/run.py) performs network fetches (urllib.request.urlopen in _verify_url_title) of arbitrary URLs taken from citations/verified.jsonl/paper_notes and parses page to decide verification_status, so it clearly ingests untrusted public web content that can influence workflow decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 05:52 AM
Issues
1