Back to skill
Skillv1.0.0
ClawScan security
Aerie · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 30, 2026, 9:05 PM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only brand information skill with no code, installation steps, credentials, or system permissions requested.
- Guidance
- This skill appears safe to install from a security-permissions perspective because it is only an informational text skill. Users should treat its brand and business claims as general content, but it does not request access to systems, files, credentials, or external services.
Review Dimensions
- Purpose & Capability
- okThe stated purpose and SKILL.md content are limited to informational brand analysis about Aerie; no capability tags, binaries, environment variables, credentials, or config paths are declared.
- Instruction Scope
- okThe read_when triggers and runtime instructions describe when to provide brand/business context and do not attempt to override user intent, force tools, or change agent behavior outside the topic.
- Install Mechanism
- okThere is no install spec and no code files; the skill consists only of SKILL.md.
- Credentials
- okThe skill does not request file, network, shell, browser, account, or local environment access.
- Persistence & Privilege
- okNo persistent memory, credentials, delegated authority, background behavior, or privileged state is requested or described.