prompt-recommendation
Warn
Audited by Snyk on Feb 16, 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 includes a "数据来源验证Prompt" (references/数据来源验证Prompt.md) and README/link-validation prompts that explicitly instruct fetching, scraping and validating arbitrary external URLs (with example Python code using requests/BeautifulSoup), so the agent would ingest untrusted public web/user-provided content as part of its workflow.
Audit Metadata