yunxiao

Warn

Audited by Snyk on Apr 27, 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 directly calls Alibaba Cloud Yunxiao/Codeup APIs (e.g., mcp__yunxiao__list_repositories, mcp__yunxiao__get_work_item, aliyun devops ListWorkitems and list_work_item_comments) to ingest MRs, work items and comments (user-generated content) which the agent is expected to read and act on per SKILL.md and references/openapi.md, so third-party content could influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 27, 2026, 03:36 AM
Issues
1