tiangong-kb-course-fulltext-fetch
Warn
Audited by Snyk on Aug 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The runtime workflow executes
./scripts/course_fulltext_fetch.sh, which calls the first-party Tiangong AI CLI with user-provideddocument_idandtagsto fetch and ingest the corresponding course full processed text.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill invokes "npx @tiangong-ai/cli@latest" at runtime (e.g., "npx @tiangong-ai/cli@latest kb course fulltext ..."), which fetches and executes remote npm package code that the wrapper requires.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata