afk
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a set of behavioral instructions that prioritize safety during unattended operation. It explicitly defines 'Blast Radius' rules to prevent unauthorized or destructive actions.
- [SAFE]: It contains specific guardrails against unauthorized privilege escalation, noting that activating the posture 'never grants permission for an operation the current task did not already authorize' and explicitly blocking actions requiring external credentials (e.g., AWS).
- [SAFE]: The posture includes mandatory verification steps, requiring the agent to run tests or builds before claiming a task is complete, which prevents hallucinations of success during autonomous runs.
- [SAFE]: The interaction model is designed to be transparent, using specific markers like
[afk mode engaged]and[AFK BLOCKED]to ensure the user can audit the agent's decisions upon return.
Audit Metadata