docs-check-zh-cn

Warn

Audited by Snyk on Mar 11, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to fetch and read external templates (e.g., the gitcode.com template URLs under "Template Selection") and the included script (scripts/check_api_doc_consistency.py) reads arbitrary provided template/doc Markdown files to extract requirements that influence checks and output, so public third‑party docs could indirectly inject instructions that change behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 01:16 AM