Skillv1.0.0

ClawScan security

Shike Zhugeliang Perspective · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignApr 16, 2026, 12:25 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only persona skill (诸葛亮视角) whose content, requirements, and behavior are coherent with its stated purpose and it does not request credentials, perform installs, or instruct access to system files or external endpoints.
Guidance: This skill appears coherent and low-risk: it's a persona that provides conservative strategic advice. Before installing, note that (1) the skill is purely instructional — it won't access your files or credentials, (2) paid consulting contact details are external channels you should vet independently, and (3) as with any advisory persona, validate critical decisions with authoritative sources or experts and avoid sending secrets or sensitive data into the prompts. If you prefer to prevent the agent from invoking skills autonomously, adjust your agent's settings.

Purpose & Capability: okThe name/description describe a decision-making persona and the SKILL.md is exactly that — heuristics, expression style, and usage examples. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope: okRuntime instructions are purely descriptive (mental models, heuristics, example prompts). They do not instruct the agent to read local files, environment variables, or to send data to external endpoints. Contact info is present only as author metadata.
Install Mechanism: okThere is no install spec and no code files to write or execute — instruction-only skills have minimal surface area and nothing is downloaded or extracted.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. Author contact information (email/WeChat) is present but is not used by the skill itself.
Persistence & Privilege: okFlags are default (always: false, user-invocable true). The skill does not request permanent presence or system-level changes. Autonomous invocation is allowed by platform default but is not combined with other concerning capabilities here.