Skillv1.0.1

ClawScan security

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

BenignApr 6, 2026, 12:49 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only informational skill about Fudan University and is internally consistent: it requests no credentials, performs no installs, and its runtime instructions are purely content, matching the stated purpose.
Guidance: This skill appears to be a harmless informational module about Fudan University. Before installing, consider: (1) provenance — the author/source/homepage are unknown, so verify facts if accuracy matters; (2) privacy — avoid sending sensitive personal data to any skill even if it looks benign; and (3) updates — because it's static content, it may become outdated. There are no requests for credentials, no installs, and no actions that would access your system or data.

Purpose & Capability: okThe name and description match the provided SKILL.md content, which is a factual/encyclopedic write-up about Fudan University. The skill does not request unrelated capabilities or credentials. Note: the skill's source/homepage is unknown, which affects provenance but not functional coherence.
Instruction Scope: okSKILL.md contains only descriptive content and 'usage' guidance for users; it does not instruct the agent to read files, access environment variables, call external endpoints, or execute commands. There is no scope creep in the instructions.
Install Mechanism: okNo install spec and no code files are present (instruction-only). This is low-risk: nothing will be written to disk or installed by the skill itself.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. No sensitive access is requested and nothing in SKILL.md attempts to read hidden config or secrets.
Persistence & Privilege: okThe skill is not marked always:true and uses default invocation settings (user-invocable, agent may invoke autonomously). Those defaults are normal; there is no evidence the skill requests elevated persistent privileges.