wewrite-topic
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on a custom command-line interface (wewrite) to fetch hot topics, perform SEO analysis, and manage task states. It instructs the agent to guide users to install this tool via 'uv tool install wewrite' or by executing a local script ('bash install.sh') if missing.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from external, untrusted sources and using this data to influence its output.
- Ingestion points: Data is collected from the web via the 'wewrite' CLI (hotspots and search-articles) and the 'WebSearch' tool.
- Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate the external web content from the agent's internal instructions.
- Capability inventory: The agent has access to 'Bash', 'Read', and 'Write' tools, which could be abused if malicious instructions are embedded in the fetched web content.
- Sanitization: There is no evidence of sanitization or validation of the external content before it is processed by the language model.
Audit Metadata