release

Warn

Audited by Snyk on Apr 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The workflow explicitly ingests user-generated content from GitHub (e.g., gh pr view <N> --repo manaflow-ai/cmux and gh issue view <N>) and parses git logs/tags to select user-facing changes and contributor handles, which the agent must read and act on to generate changelogs and credit contributors, creating a clear path for untrusted third-party content to influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 7, 2026, 09:35 AM
Issues
1