poteto-mode
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a set of 'Non-negotiables' and 'Principles' aimed at ensuring high-quality software engineering. The instructions focus on structured todolists, scientific debugging, and thorough verification of work.\n- [COMMAND_EXECUTION]: The playbooks instruct the agent to use standard CLI tools such as git and the GitHub CLI (gh) for repository management and PR workflows. It also mentions internal tools like 'spawn-codex-worker' for task delegation within its specific runtime environment.\n- [PROMPT_INJECTION]: The skill instructions define an operational style ('poteto-mode') and prioritize specific principles (e.g., Laziness Protocol, Foundational Thinking). These do not attempt to bypass core safety guardrails or exhibit adversarial behavior.\n- [DATA_EXFILTRATION]: Analysis did not reveal any patterns associated with unauthorized data access or exfiltration. The skill's network activities are restricted to legitimate development actions like interacting with GitHub.
Audit Metadata