gomtm-agent-workflow
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.78). Required workflow routes human-authored text from GitHub Issue comments (approval gate: “记录 approval URL/text”, “人类回复 ‘批准执行/调整方案/暂缓’”) into the agent’s runtime context, creating indirect prompt-injection exposure via GitHub comment body text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata