Back to skill
Skillv1.0.0
ClawScan security
thesis-writing-advisor · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 29, 2026, 11:02 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's files and runtime instructions match its stated purpose (psychology/undergraduate thesis advising), request no credentials or installs, and do not contain actions outside that scope.
- Guidance
- This skill appears internally consistent and limited to producing thesis topics, method choices, chapter plans, and writing guidance for undergraduate psychology and related social-science topics. Before installing or using it: (1) remember generated text is only a scaffold — verify citations, accuracy, and adapt wording to your advisor and school rules; (2) avoid submitting AI-generated prose verbatim as your own work (academic honesty); (3) for any design that touches human subjects or mental-health interventions, confirm ethical/IRB requirements, include consent and referral provisions, and do not treat the design as evidence of effectiveness; (4) check references and DOIs if you need formal citations; (5) there are no network endpoints, secrets, or installs in the package, but always review outputs for sensitive personal data before sharing. Overall this skill looks safe from a coherence/security standpoint, but use its content responsibly with respect to academic integrity and participant safety.
Review Dimensions
- Purpose & Capability
- okName, description, and included reference documents (chapter plans, psychology guide, qualitative methods, sample papers) are coherent with the stated goal of producing undergraduate thesis topics, proposals, and writing guidance. The skill does not request unrelated binaries, environment variables, or config paths.
- Instruction Scope
- okSKILL.md gives concrete instructions for extracting user inputs, selecting methods, and producing full thesis guidance. It references only local reference files and contains explicit cautions (ethics, limitations). It does not instruct reading arbitrary system files, contacting external endpoints, or accessing credentials.
- Install Mechanism
- okNo install spec or code files that would be written to disk; this is an instruction-only skill that uses bundled reference documents. Low installation risk.
- Credentials
- okThe skill requires no environment variables, no credentials, and no config paths. Requested access is proportionate to an instruction-only advisory skill.
- Persistence & Privilege
- okalways is false and the skill is user-invocable; it does not request permanent presence, nor does it attempt to modify other skills or system-wide settings. Autonomous invocation is allowed by platform defaults but not escalated here.