rpi
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill coordinates the execution of local CLI tools such as git, ao, and bd, as well as repository-specific scripts for context windowing and validation (e.g., generate-context-shards.py). This behavior is consistent with its purpose as an automated development orchestrator and utilizes local infrastructure.
- [PROMPT_INJECTION]: The instructions contain directives for autonomous execution and adherence to a three-phase lifecycle (discovery, implementation, validation). These instructions are operational requirements for the orchestrator's task management rather than attempts to bypass the agent's core safety guidelines.
- [DATA_EXFILTRATION]: File system operations are localized to project metadata, execution packets, and agent-generated reports within the .agents/ directory. There is no evidence of sensitive data, such as environment variables or credentials, being accessed for transmission to external hosts.
- [REMOTE_CODE_EXECUTION]: The skill relies exclusively on local scripts and predefined sub-skills. No patterns of downloading or executing code from remote or untrusted sources were identified.
Audit Metadata