agency-technical-writer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions and documentation templates designed to guide an AI in writing technical content. It does not include executable scripts, automation code, or commands that would be run on a host system.
- [INDIRECT_PROMPT_INJECTION]: The agent is instructed to analyze external data such as GitHub issues, support tickets, and source code to identify documentation gaps. While this exposes the agent to untrusted external data, the risk is inherent to the task of technical writing, and the instructions do not facilitate any downstream exploitation or unsafe command execution based on that data.
- [CREDENTIALS_UNSAFE]: The skill includes examples of configuration files (e.g., Docusaurus config) that use placeholders like
YOUR_APP_IDandYOUR_SEARCH_API_KEY. These are standard documentation practices and do not constitute a credential leak.
Audit Metadata