wechat-article-search-api-skill
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill interacts with the official BrowserAct API endpoints (
api.browseract.com). All network communication is directed to the vendor's established infrastructure, which is consistent with the skill's stated purpose of content extraction. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it retrieves full article body text and metadata from external WeChat pages.
- Ingestion points: External WeChat article data is fetched by the
scripts/wechat_article_search_api.pyscript via the BrowserAct API. - Boundary markers: The script does not currently implement specific boundary markers or delimiters around the retrieved external content in its output.
- Capability inventory: The skill uses a Python script to perform network requests (
requests.get,requests.post) and prints results to the terminal for the agent to process. - Sanitization: The script performs no sanitization on the article body text retrieved from the API before printing it to standard output.
- [COMMAND_EXECUTION]: The skill uses a standard Python execution pattern to run its core logic. The command
python -u ./scripts/wechat_article_search_api.pyis invoked with user-provided keywords and limits, representing normal functional behavior for an AI agent skill.
Audit Metadata