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-provided document_id and tags to 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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 16, 2026, 03:01 AM
Issues
2
Security Audit — snyk — tiangong-kb-course-fulltext-fetch