weekly-report
Warn
Audited by Snyk on Mar 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches user-generated third-party content via "3d. GitHub Activity (if
ghavailable)" using gh to read PRs/issues and via "3e. 云效 Activity (if yunxiao skill available)" by invoking the yunxiao skill, and it directly ingests and acts on that content to draft the report and influence subsequent actions, so untrusted external content can alter agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata