Skillv0.1.2

ClawScan security

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

Scanner verdict

BenignApr 30, 2026, 10:46 AM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only academic paper‑writing skill that is coherent with its stated purpose, requests no credentials or installs, but it references external docs and includes a trigger phrase about removing AI traces which you should be aware of.
Guidance: This skill is an instruction-only writing helper and appears internally consistent. Before installing or using it, consider: (1) outputs should be reviewed for factual and citation accuracy — the skill provides templates but cannot verify claims or results; (2) the 'remove AI traces' trigger indicates it can be used to alter text to look less AI‑generated — using that capability may violate academic integrity or submission policies, so use with caution; (3) the SKILL.md references an external relative document (terminology.md) that is not included, so some referenced resources may be missing. No credentials, installs, or system access are requested.

Review Dimensions

Purpose & Capability: okName/description (3D vision & graphics paper writing) match the SKILL.md content: templates, section guidance, metrics and terminology. The skill asks for no binaries, env vars, or installs, which is proportionate for a writing/template helper.
Instruction Scope: noteSKILL.md contains detailed templates and writing rules only — it does not instruct the agent to read system files, environment variables, or send data to external endpoints. Two items to note: (1) it references an external relative path (../../references/terminology.md) which does not exist inside this instruction-only package and therefore cannot be resolved by the agent unless additional resources are provided; (2) the trigger set includes '去AI痕迹' ('remove AI traces'), implying the skill may be used to help mask AI authorship — this is within the scope of a writing assistant but has ethical/academic-integrity implications rather than a technical incoherence.
Install Mechanism: okNo install spec or code files are present; nothing is written to disk or downloaded, which is low risk and consistent with an instruction-only writing assistant.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. That aligns with the writing-oriented functionality.
Persistence & Privilege: okalways is false and the skill does not request elevated or persistent system privileges. It does not modify other skills or system settings (no install steps).