Back to skill
Skillv0.1.0
ClawScan security
ton · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 18, 2026, 12:39 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is internally consistent and only exposes a small local script that prints static brand/feature information — it does not request credentials, reach out to the network, or perform unexpected actions.
- Guidance
- This skill is informational: it runs a local shell script that prints static text/JSON about the 'ton' namespace. If you install it, review scripts/ton-info.sh (already included) to confirm you’re comfortable with it (it does not perform network calls or access secrets). Note it is Linux-only and declares exec permission for its script, which is expected for this behavior.
Review Dimensions
- Purpose & Capability
- okThe name/description claim an informational 'ton' namespace for audio/media tools and the included script and docs only provide brand, feature, and JSON metadata — these requirements match the stated purpose.
- Instruction Scope
- okSKILL.md instructs the agent to run scripts/ton-info.sh with optional flags; the script only outputs static text/JSON and does not read other files, environment variables, or contact external endpoints.
- Install Mechanism
- okThere is no install spec (instruction-only plus a small local script). Nothing is downloaded or written to disk by an installer, so installation risk is minimal.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. The single script does not access secrets or system configs.
- Persistence & Privilege
- okalways is false and the skill requests only exec permission for its local script. It does not modify other skills or system-wide settings and has no elevated persistence.