autoresearch

Warn

Audited by Snyk on Oct 26, 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). The workflow optionally queries Exa for adversarial testing patterns via an external API (https://api.exa.ai/search), exposing the benign AI agent to outsider-authored free text from search results.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.70). The script scripts/eval_gen.py queries 'https://api.exa.ai/search' during setup to fetch testing patterns, constituting a weak/unknown third-party operational dependency.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 26, 2026, 06:33 PM
Issues
2