AURA
Analysis
AURA is a coherent, instruction-only personality configuration skill, with the main caution that it creates a persistent workspace file that can influence future agent behavior.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
"How much should I act on my own vs ask permission?" ... "autonomy | Asks permission | Acts independently"
The skill explicitly allows the user to tune how independently the agent behaves. This is central to the personality configuration purpose, but it can affect when the agent asks for permission.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
"Creates or updates `AURA.yaml` in workspace" and "If AURA.yaml exists in workspace, read it at session start and apply the personality traits to all responses."
The skill stores persistent personality instructions in a workspace file and recommends loading them at future session startup. This is disclosed and purpose-aligned, but the file becomes reusable context that can shape later behavior.