instruction-eval

Warn

Audited by Snyk on Aug 11, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). Outsider-authored free text is ingested only insofar as the user supplies the prompt text for the run (via the prompts set passed into run_ab.py), and the required workflow does not automatically read unsolicited external free-text sources like inboxes/chat/GitHub/Jira.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 02:15 PM
Issues
1
Security Audit — snyk — instruction-eval