traditional-chinese-medicine-master
Warn
Audited by Snyk on Aug 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In cli/protocol/agentic.sh, the workflow reads the outsider-authored “PROBLEM” via ms_read_multiline from standard input and then incorporates it into the generated findings/report (ms_buffer_append “## 问题” and later “发现” loops), even though it does not fetch URLs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata