worker-handover

Warn

Audited by Snyk on Feb 16, 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 reads and ingests handover text directly from GitHub issue comments (user-generated, potentially public content) and expects the agent to interpret that comment body to continue work, exposing it to untrusted third-party input.

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

  • Potentially malicious external URL detected (high risk: 1.00). The skill fetches handover content at runtime from the GitHub issues API (gh api "/repos/$OWNER/$REPO/issues/$ISSUE/comments" — https://api.github.com/repos/$OWNER/$REPO/issues/$ISSUE/comments), and the retrieved comment body directly supplies the replacement worker's prompts/instructions and is required for continuation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:03 AM