Back to skill
Skillv1.0.0

ClawScan security

Smooth Browser Use · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 29, 2026, 2:54 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's instructions, requirements, and scope are coherent with its stated purpose: it is an instruction-only guide for reliable, human-like browser interactions and page recovery.
Guidance
This skill is internally consistent with its stated purpose. Before installing, confirm your agent/platform provides the browser primitives the instructions assume (get_app_state, set_value, clipboard access, and a way to synthesize real paste/keyboard events). Be mindful that the skill explicitly directs putting long text on the system clipboard and pasting into web pages — do not use it to paste sensitive secrets unless you trust the target page. Note the SKILL.md uses macOS shortcut examples (Cmd+V); adapt usage for other OSes (e.g., Ctrl+V). Also consider provenance: the source and homepage are unknown, so test the skill in a safe/non-sensitive environment to verify behavior before using it on real accounts or sensitive content.

Review Dimensions

Purpose & Capability
okName/description (smooth, human-like browser interactions and page recovery) aligns with the SKILL.md instructions. No unrelated binaries, credentials, or installs are requested.
Instruction Scope
noteInstructions stay within browser interaction and recovery scope (click visible controls, paste via clipboard, verify page state, refresh). They reference platform/browser primitives like get_app_state, set_value, accessibility tree, and use of the system clipboard and Cmd+V; these are expected for a browser automation skill but are operational assumptions the agent/platform must provide. Be aware clipboard use can move sensitive data into web pages.
Install Mechanism
okInstruction-only skill with no install spec or downloaded code; nothing is written to disk or fetched during install.
Credentials
okNo environment variables, credentials, or config paths are requested. The SKILL.md does not ask for secrets or unrelated credentials.
Persistence & Privilege
okalways is false and there is no indication the skill modifies other skills or system-wide settings. Autonomous invocation is allowed (platform default) and appropriate for this kind of helper.