wechat-article-writer
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill incorporates
web_fetchand web search capabilities to retrieve research materials from user-provided URLs and search engine results. This is a legitimate functional requirement for a content creation assistant. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes content from external websites which could contain adversarial instructions.
- Ingestion points: Untrusted data is ingested via
web_fetchand web search results as described in Step 1 and Step 2 ofSKILL.md. - Boundary markers: The skill relies on 'Quality Checklist' (references/quality-checklist.md) and 'Fact Checking' instructions rather than technical delimiters (like XML or Markdown blocks) to isolate external content.
- Capability inventory: The skill is restricted to information retrieval tools. It does not contain instructions for subprocess execution, file system modification, or network exfiltration of sensitive local data.
- Sanitization: The instructions emphasize 'Source Verification' and 'Fact-checking' as manual verification steps to ensure that retrieved data is accurate and legitimate before being used in the final article.
Audit Metadata