wechat-article-writer
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: A thorough audit of the skill instructions and reference materials found no evidence of malicious intent. The skill follows established patterns for content generation and research.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its reliance on external web data fetched via
web_fetchandexa:web_search_exa. 1. Ingestion points:web_fetchandexa:web_search_exacalls in SKILL.md used for material analysis and research. 2. Boundary markers: Not present; the skill does not explicitly instruct the model to ignore instructions found within external content. 3. Capability inventory: The skill utilizes search, web fetching, and memory MCP tools. 4. Sanitization: No explicit validation or filtering of fetched web content is performed.
Audit Metadata