llm-project-setup
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The analyzed skill consists entirely of documentation and workflow instructions in Markdown format. There are no scripts, automated commands, or executable components within the skill itself.
- [COMMAND_EXECUTION]: The documentation includes example shell commands (e.g.,
ragbot compile,ragbot index). These are provided as guidance for the user to run manually in their own local environment and are not executed by the agent. The 'ragbot' tool itself is referenced as an external dependency of the user's workflow. - [DATA_EXFILTRATION]: No patterns of data exfiltration were detected. The skill describes a local compilation and manual upload process for configuration files ('all-knowledge.md', 'claude.md', etc.).
- [PROMPT_INJECTION]: No malicious prompt injection or override instructions were found. The 'Custom instructions' sections are descriptive guides for platform configuration.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any automated external downloads. It references GitHub synchronization as a manual setup option for users of the Claude platform.
Audit Metadata