wechat-article-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Detected an Indirect Prompt Injection vulnerability surface (Category 8). The skill is designed to ingest and process data from external, untrusted sources which could contain malicious instructions.
- Ingestion points: The skill utilizes the
web_fetchtool in Step 1 to retrieve content from user-provided URLs. - Boundary markers: Absent. There are no instructions to the agent to treat fetched content as data only or to ignore embedded commands (e.g., 'ignore previous instructions').
- Capability inventory: The agent has access to
web_fetch,exa:web_search_exafor further information gathering, andmem0-memory-mcpfor long-term storage of preferences and data. - Sanitization: Absent. No logic is present to sanitize or filter the content retrieved from external websites before processing it.
- EXTERNAL_DOWNLOADS (LOW): The skill performs network operations via
web_fetchandexa:web_search_exa. While these are core to the skill's purpose of researching and writing articles, they involve connecting to and downloading data from arbitrary external domains.
Audit Metadata