wechat-article-pro
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate automation tasks for the WeChat Official Account platform. No malicious instructions or hidden behaviors were found in the skill metadata or logic.
- [DATA_EXFILTRATION]: The skill uses web_fetch for research and interacts with mp.weixin.qq.com for publishing. There is no evidence of unauthorized credential harvesting or sensitive file access.
- [PROMPT_INJECTION]: The skill contains clear instructional guidelines for writing style and layout without attempting to bypass safety filters or override agent constraints.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests external data from the web, the workflow involves generating a draft for user review within the official platform, maintaining a safe operation boundary.
- Ingestion points: web_fetch search results in SKILL.md
- Boundary markers: Absent
- Capability inventory: browser interaction and draft saving on mp.weixin.qq.com in SKILL.md
- Sanitization: Absent
Audit Metadata