v3.0.0

Avoid AI Writing

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:08 AM.

Analysis

This is an instruction-only writing-editing skill with no code, credentials, tools, or hidden data access in the provided artifacts.

GuidanceThis skill appears safe for its stated purpose: editing text to sound less AI-generated. Before installing manually, make sure you trust the GitHub source or use the ClawHub package.

Findings (1)

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.

Abnormal behavior control

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.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceHighStatusNote

README.md

git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.openclaw/skills/avoid-ai-writing

The README offers a manual installation path from an external GitHub repository into the assistant's skills directory. This is normal for a portable skill and no unsafe behavior is shown, but it still requires trusting the repository source.

User impactIf installed manually from GitHub, the user is trusting that repository's contents match the reviewed skill.

RecommendationPrefer installing from ClawHub when available, or inspect the repository contents before cloning it into an assistant skills directory.