Back to skill
Skillv1.0.0
ClawScan security
Cambridge Uni · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 30, 2026, 10:04 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only informational skill about the University of Cambridge that requests no credentials, installs, or system access and its behavior matches its description.
- Guidance
- This skill is internally consistent and simply provides reference content about Cambridge University. Before installing, consider: (1) verify factual claims you care about (the skill is static text and may be simplified or contain minor inaccuracies), (2) watch for future updates—if an update later requests environment variables, downloads, or an install script, review those changes carefully, and (3) autonomy is enabled by default (the agent may call the skill when relevant); that is normal for skills but if you want to restrict automatic use, disable autonomous invocation in your agent settings.
- Findings
[no_code_no_findings] expected: The regex-based scanner had no code files to analyze; this is expected for an instruction-only informational skill. No suspicious patterns were found because there was nothing to scan.
Review Dimensions
- Purpose & Capability
- okThe name and description (Cambridge history, achievements, collegiate system, Silicon Fen) align with the SKILL.md content. The skill requests no binaries, env vars, or config paths, which is appropriate for an informational/reference skill.
- Instruction Scope
- okSKILL.md contains static content and a small set of 'read_when' triggers describing when the skill should be used. It does not instruct the agent to run shell commands, read files, access environment variables, or transmit data to external endpoints.
- Install Mechanism
- okNo install specification or code files are present. This reduces surface risk because nothing is written to disk or installed.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. There is no over-broad or unexplained credential request.
- Persistence & Privilege
- okalways is false and the skill is user-invocable. disable-model-invocation is false (normal). The skill does not request permanent presence or system modifications.