byted-volcengine-alert-inspection-analyzer
Warn
Audited by Snyk on Jul 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md:41-60 describes fetching Feishu group messages via
feishu_im_user_get_messages, and scripts/alert_inspection.py:322-326 loads that tool-returned JSON and converts outsider-authoredcontentinto LLM-readable strings (e.g.,normalized[*].contentand fields extracted from it) that are then used to generatereport.md.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata