NoPUA
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 agent may keep working through more attempts instead of stopping quickly or asking for help.
This changes the agent's stopping condition by encouraging continued attempts after failure. It is aligned with the skill's anti-give-up purpose, but could make the agent continue longer than the user expects.
Don't say "I can't solve this" until you've exhausted every approach.
Use clear user instructions such as time limits, attempt limits, or 'ask before continuing' when a task has cost, safety, or production impact.
The agent may read project files, search, or run verification commands before asking follow-up questions.
The skill explicitly encourages proactive use of tools before asking the user. This is expected for a debugging/productivity coaching skill, but it can broaden activity if the agent has powerful local or remote tools.
You have search, file reading, command execution tools. Before asking the user, investigate with tools first.
Install only if you are comfortable with proactive investigation, and require approval for destructive, costly, credentialed, production, or broad filesystem actions.