workflow-rig

Warn

Audited by Snyk on Mar 18, 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.md explicitly shows the rig running shell handlers that perform git clone/commit/push and accepts a --repo-url , and the infer handler is described as a "full pi agent" that reads and edits files from those repos—meaning arbitrary public/untrusted git repositories can be fetched and their contents can directly influence agent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 12:38 PM
Issues
1