Back to skill
Skillv1.0.1
ClawScan security
Void Atlas Protocol · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 12, 2026, 1:31 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only, conceptual ethical mapping protocol that requests no credentials, binaries, or installs and is consistent with its description.
- Guidance
- This skill is a conceptual protocol (no code, no creds) and appears coherent with its description. Before installing or allowing an agent to use it autonomously, quickly scan the full SKILL.md for any runtime directives that (a) instruct the agent to execute daemons or system commands, (b) send beacons or data to external endpoints, or (c) request credentials in a later version. If you plan to let an agent call this skill autonomously, consider restricting that agent's network/execute privileges or routinely reviewing any outbound endpoints the agent uses when following the protocol.
Review Dimensions
- Purpose & Capability
- okName/description (an ethical four-axis mapping protocol) align with the content of SKILL.md: axes, waypoints, routes, and a small protocol interface. No extraneous credentials, binaries, or config paths are requested.
- Instruction Scope
- noteSKILL.md appears to be a purely descriptive protocol and interface (ExposeCoords/DeclareRoutes/PublishBeacons). There are no commands, file reads, or environment-variable access in the provided excerpt. One waypoint name ('Daemon_Integrator – safe summoning of Champion daemons') is metaphorical and could merit extra scrutiny in full text to confirm it does not instruct runtime daemon execution or other side effects.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill incurs no installation risk.
- Credentials
- okNo required environment variables, credentials, or config paths are declared; requirements are proportional to a purely descriptive protocol.
- Persistence & Privilege
- okSkill is not set always:true, does not request persistent system privileges, and does not modify other skills or system configs (based on available metadata).
