behavioral-evals

Warn

Audited by Snyk on Apr 8, 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 required workflows (references/fixing.md and references/promoting.md) explicitly instruct fetching and auditing nightly results from a public GitHub URL using the gh CLI (e.g., https://github.com/.../evals-nightly.yml), which requires the agent to ingest and interpret third-party, user-generated CI/log content that can materially influence debugging and promotion decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 8, 2026, 01:34 PM
Issues
1