gpt-go
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
The assistant may continue working from short prompts like “continue” or “fix it” without asking routine follow-up questions.
The skill intentionally changes the agent's stopping and continuation behavior for the current conversation. This is disclosed and central to the skill's purpose, but users should understand the mode remains active until turned off.
Keep it active until the user turns it off... Treat messages like these as authorization to proceed
Use this mode only when you want a faster execution style, and explicitly turn it off or ask for step-by-step collaboration when you want more confirmations.
If the assistant has tools available, it may inspect the working environment and take routine actions without asking first.
The skill biases the agent toward direct tool-based inspection and action. This is purpose-aligned for an execution mode and is paired with pause boundaries, but it can reduce user confirmation for low-risk actions.
Use tools to inspect and act whenever possible. Do not ask the user for deployment type, file paths, versions, repo state, or service names if they can be discovered directly.
Before invoking the skill, make sure the current task scope is clear and rely on the stated pause boundaries for sensitive or high-impact actions.