Back to skill
Skillv1.0.0
ClawScan security
Account Strategist · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 10, 2026, 9:57 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only account-strategy agent made of documentation and templates; it requests no credentials, installs no software, and its content matches its stated purpose.
- Guidance
- This skill is documentation and templates for account-strategy work and appears internally consistent. Before you enable it: (1) note the source is listed as unknown — if provenance matters to you, verify the publisher. (2) Do not provide sensitive customer PII or credentials to the agent when using these playbooks. (3) If you prefer to prevent autonomous runs, restrict model-invocation for this skill in your agent settings; otherwise it will be able to be invoked by the agent (this is the platform default).
Review Dimensions
- Purpose & Capability
- okName and description match the provided agent identity, playbooks, and templates. There are no unrelated binaries, environment variables, or config paths requested.
- Instruction Scope
- okSKILL.md and the other docs are behavioral guidelines, templates, and playbooks for account strategy. They do not instruct the agent to read arbitrary files, access credentials, call external endpoints, or exfiltrate data.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only, so nothing is downloaded or written to disk by an installer.
- Credentials
- okThe skill does not declare or require any environment variables, secrets, or credentials. Requested scope is minimal and appropriate for a documentation-only agent.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system privileges or modify other skills' configs. Model invocation is enabled (the platform default) but that is appropriate for this type of agent.