action-audit

Warn

Audited by Snyk on Apr 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to fetch and parse workflow files and action repos via gh search code and gh api repos/<owner>/<repo>/commits/<ref>, which ingests user-generated content from public GitHub repositories (third-party actions and workflow files) and uses those results to decide remediation and resolved SHAs.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 17, 2026, 02:15 PM
Issues
1