Back to skill
Skillv1.0.0
ClawScan security
thesis-methodology-writer · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 5:54 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only Chinese thesis-methodology writer whose declared inputs and behavior match its stated purpose and it does not request extra credentials, installs, or external endpoints.
- Guidance
- This skill appears coherent and does not request credentials or install code. Before installing, consider: 1) Academic integrity — using it to write a thesis chapter may violate your institution's rules; use it as a drafting aid and verify originality. 2) Data privacy — if you provide participant-level details, anonymize or omit sensitive personal data (the skill will include ethics and data-security wording but will not protect actual data). 3) Accuracy and reproducibility — the skill will infer research type and insert placeholders when details are missing, so provide concrete info (sample size, instruments, analysis plan) to avoid incorrect assumptions. 4) Citation and permissions — the skill may produce text that requires proper citation or permission for instruments; verify and cite sources. Finally, note that as an instruction-only skill it does not execute external code or exfiltrate data, but the content it generates should be reviewed for correctness and compliance with your advisor/institution.
Review Dimensions
- Purpose & Capability
- okThe name and description match the actual contents: an instruction-only writer for methodology chapters. The skill requires no binaries, env vars, or config paths and its included reference material (methodology-writing-guide.md) is directly relevant. There are no unexpected permissions or unrelated requirements.
- Instruction Scope
- okSKILL.md confines runtime behavior to drafting methodology sections, determining research type from user-provided study details, and using the included reference file. It does not instruct reading system files, environment variables, or sending data to external endpoints. It does allow inferring missing inputs and using placeholders, and it restricts follow-up questions to at most one concise query when needed.
- Install Mechanism
- okNo install spec and no code files — the skill is instruction-only so nothing is downloaded or written to disk during installation.
- Credentials
- okNo environment variables, credentials, or config paths are requested. The input extraction list asks for thesis-related content (instruments, sample, ethics) which is appropriate and proportional for generating methodology text.
- Persistence & Privilege
- okalways is false and the skill does not request elevated persistence or modify other skills. Normal autonomous invocation is allowed (disable-model-invocation is false) which is platform-default and not, by itself, a concern.