self-ship

Warn

Audited by Snyk on Nov 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.30). The required workflow waits on CI and review bots for a GitHub pull request and claims an issue from the repo's issue tracker, so outsiders can post PR comments and issue text that the run reads without the agent selecting a specific item.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The skill instructs running npx skills@latest add toy-crane/skills to install missing required skills during setup, which is an inbound repository-sourced dependency, and since toy-crane is an individual-owned repository without established first-party provenance, it is unofficial but reputable with no concrete warning sign, so the tier is medium.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 13, 2026, 07:13 AM
Issues
2