search-and-fork

Warn

Audited by Snyk on Mar 11, 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). This skill uses the search_open_source_repositories tool to fetch public Gitee repositories and explicitly instructs the agent (SKILL.md Steps 2–3) to read/evaluate README, license, activity, and other repo content — untrusted, user-generated content that can materially influence which repo is chosen and what actions the agent takes, so it could enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 01:06 AM