Back to skill
Skillv1.0.0
ClawScan security
paper-assistant · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 11, 2026, 7:42 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's requested resources and runtime instructions are consistent with an academic writing assistant and do not request unnecessary credentials, installs, or system access.
- Guidance
- This skill appears coherent and low-risk: it only provides writing assistance and asks for no credentials or installs. Before using, consider: do not paste sensitive or unpublished data you don't want processed; verify any factual claims, citations, and statistics the assistant produces (the SKILL.md already forbids fabricating references/data, but model hallucinations can occur); if you need up-to-date journal policies or recent literature, be prepared to supply sources or enable a trusted web retrieval mechanism; and run outputs through plagiarism checks and your institution's ethics/publishing rules before submission.
Review Dimensions
- Purpose & Capability
- okThe name and description (论文助手) match the SKILL.md content: guidance on topics, outlines, abstracts, literature review, methods, results discussion, polishing, and submission prep. There are no unrelated required binaries, environment variables, or config paths that would be unnecessary for this purpose.
- Instruction Scope
- okAll runtime instructions in SKILL.md stay within the scope of assisting academic writing. The file defines clear workflows, output preferences, and explicit prohibitions against fabricating references or data. It does not instruct the agent to read system files, access unrelated environment variables, or send data to external endpoints.
- Install Mechanism
- okThis is an instruction-only skill with no install spec and no code files to execute. That minimizes installation risk—nothing will be downloaded or written to disk by the skill itself.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths. This is proportionate to its described functionality (text generation and editing).
- Persistence & Privilege
- okalways is false (no forced inclusion). disable-model-invocation is false (normal: agent may call the skill autonomously), which is expected for skills. The skill does not request to modify other skills or system-wide config.