ToneClone CLI
PassAudited by ClawScan on May 1, 2026.
Overview
No suspicious behavior was found; the skill is a user-invoked wrapper for ToneClone’s CLI, but it does require installing an external CLI and logging into a ToneClone account that uses personas and knowledge cards.
This skill appears coherent and purpose-aligned. Before installing, make sure you trust the ToneClone CLI/Homebrew tap and are comfortable logging into ToneClone. Review what is stored in your personas and knowledge cards, and check generated messages before sending or posting them.
Findings (3)
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.
Installing the skill may require installing and trusting the ToneClone command-line tool from its Homebrew tap.
The skill instructs users to install an external CLI from a Homebrew tap. This is disclosed and purpose-aligned, but it depends on trusting that external package source.
brew tap toneclone/toneclone brew install toneclone
Install only if you trust ToneClone and the Homebrew tap; review the linked documentation or source if you need higher assurance.
The CLI will operate with access to your ToneClone account resources, such as personas and knowledge cards.
The skill requires logging into a ToneClone account so the CLI can use account-specific personas and knowledge cards. This credential use is expected for the integration.
ToneClone requires an account and trained personas... Authenticate: ```bash toneclone auth login ```
Use the normal ToneClone login flow, avoid sharing credentials manually, and review what personas or knowledge cards the account contains.
Generated text may reflect whatever information is stored in your ToneClone personas or knowledge cards.
The skill relies on persistent persona and knowledge-card context to shape generated text. This is central to the purpose, but stored context can contain sensitive or outdated information that affects future outputs.
Use trained personas for different writing styles and knowledge cards for context.
Keep personas and knowledge cards accurate, remove sensitive material you do not want reused, and review generated content before sending or publishing.