daily-digest

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md Steps 2–4 require calling Gitee MCP Server APIs (list_user_notifications, list_repo_pulls, list_repo_issues) to fetch unread notifications, PRs, and issues—user-generated, public content the agent reads and uses to prioritize and decide actions, so it can convey untrusted instructions that influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 01:21 PM