agents-docs
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official domains including
developers.openai.comandcode.claude.com. These are well-known and reputable sources for product documentation. - [COMMAND_EXECUTION]: The instructions direct the agent to use standard utilities like
curlfor fetching web content andrg(ripgrep) for searching downloaded text. These operations are scoped to documentation retrieval and information processing within temporary operating system locations, avoiding the repository or skill installation directory. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web pages. The risk associated with this ingestion is low as the instructions strictly limit the sources to official documentation domains, which are controlled by reputable organizations.
Audit Metadata