brain-sync

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly pulls and rebases from the remote repository specified in Step 3 (Option B) and Step 4-1 ("git ... fetch origin main" / rebase origin/main), meaning it ingests content from a user-provided GitHub URL which could be untrusted user-generated data that would update ~/.brain and thus materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 10:07 AM