Back to skill
Skillv0.1.0
ClawScan security
Go To Market · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 16, 2026, 9:27 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is an instruction-only go-to-market playbook that asks for no installs, credentials, or special system access and is consistent with its stated purpose.
- Guidance
- This skill appears coherent and low-risk because it's a text-only GTM playbook that asks for nothing sensitive. Still: avoid pasting proprietary secrets, credentials, or PII into prompts when using it; review any operational or execution recommendations before acting on them (the skill may suggest actions like outreach or ad spend that require human oversight). If you plan to connect the agent to external services or give it permission to act autonomously, review those agent integrations separately—this skill itself does not require or request them.
Review Dimensions
- Purpose & Capability
- okThe name and description (GTM strategy) match the SKILL.md content: templates, channel selection, positioning, and execution guidance. There are no unrelated requirements (no binaries, env vars, or installs).
- Instruction Scope
- okRuntime instructions are a step-by-step GTM playbook and do not instruct the agent to read files, access credentials, call external endpoints, or transmit data. The guidance is limited to planning, templates, and questions to ask customers.
- Install Mechanism
- okNo install specification or code files are present. Being instruction-only minimizes on-disk risk and nothing is downloaded or executed by the skill itself.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths—appropriate for a planning/playbook skill that only generates text-based guidance.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system privileges or modify other skills. disable-model-invocation is false (normal); note this means an agent with autonomous invocation could call the skill, but that is expected behavior for a user-invocable instruction-only skill.