Skillv1.0.0

ClawScan security

Story Chain Multiverse · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

BenignFeb 26, 2026, 3:23 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill is an instruction-only interactive story generator whose requested files and runtime instructions match its description and do not ask for unrelated credentials, installs, or system access.
Guidance: This skill appears internally consistent with its purpose: it only uses local reference files and contains no installs, network endpoints, or secret requests. Before installing, consider: (1) the skill supports optional R18/adult content that is only enabled when the player explicitly asks — enable adult routes only if appropriate for your environment; (2) it includes examples and a 'fanfiction'/同人 option referencing existing IPs (e.g., Marvel, anime) — be mindful of copyright or policy constraints if you plan to publish generated content; (3) because it is instruction-only and can run autonomously by default, monitor how the agent invokes it in multi-skill/autonomous workflows to ensure it is used only when intended. No other security red flags were found.
Findings: [no_code_to_scan] expected: The regex-based scanner had no code files to analyze — this is expected for an instruction-only skill. Pre-scan injection signals: none detected.

Purpose & Capability: okName/description (interactive multi-genre story chain) match the included SKILL.md and reference files (templates, name lists, kink list, sample outputs). There are no unrelated required binaries, env vars, or config paths.
Instruction Scope: okRuntime instructions stay within the storytelling domain: produce opening paragraphs, per-turn replies of 180–350 Chinese characters, present 3–4 choice options, allow explicit R18 only on user opt-in, and (on termination) produce a full mid-length rewrite. The SKILL.md suggests reading the local references/ folder (which is provided) — this is coherent with generating consistent content.
Install Mechanism: okNo install spec and no code files — instruction-only. Nothing is downloaded or written by an installer, which minimizes filesystem and network risk.
Credentials: okThe skill requires no environment variables, credentials, or config paths. The only data it references are local bundled files (references/*). No requests for external tokens or unrelated secrets are present.
Persistence & Privilege: okalways is false and the skill does not request persistent system-level presence or modification of other skills. It does not instruct modifying agent/system config or storing tokens beyond its own runtime use.