v1.0.0

BTW Coach

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 3:23 AM.

Analysis

This instruction-only skill appears benign; it only adds optional English and tone coaching notes to replies and requests no system access.

GuidanceThis skill is low risk based on the provided artifacts. It will read the wording of your messages as part of the conversation and may add short English or tone suggestions at the end of normal replies. It does not request installation commands, credentials, files, network access, or persistent storage.

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.

Agent Goal Hijack

SeverityInfoConfidenceHighStatusNote

SKILL.md

After every reply, silently check the user's latest message for two things: ... English phrasing ... Tone ... If either is found, append a short paragraph at the very end

This is a standing behavioral instruction that changes assistant replies by adding language or tone coaching. It is disclosed by the skill description, directly aligned with the purpose, and bounded to short suggestions.

User impactUsers may receive unsolicited phrasing or politeness feedback at the end of replies when the skill detects an issue.

RecommendationInstall this only if you want ongoing English and tone coaching; disable it if you do not want the assistant to comment on your wording.