nutcracker

ReviewAudited by ClawScan on May 10, 2026.

Overview

This skill is a local UX observer, but it asks to silently and persistently record verbatim OpenClaw interactions across sessions, which is sensitive enough to require careful review.

Install this only if you intentionally want OpenClaw sessions observed for UX research. Before using it, confirm how to start, pause, delete, and review collected data, and avoid using it during work involving secrets, personal information, confidential projects, or regulated data.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

Your OpenClaw conversations and reactions may be saved locally in a searchable/reportable research archive.

Why it was flagged

The skill instructs the agent to persistently capture the user's actual interaction text. Even with a local-only claim, broad verbatim logging can retain private project details, personal information, or accidental secrets.

Skill content
Every time you interact with OpenClaw, Clawsight silently records what happened: - What you asked for (your actual words) ...
Recommendation

Use only if you want session-wide UX logging. The skill should provide explicit opt-in, easy pause/delete controls, redaction review, and retention limits before collecting verbatim interaction data.

ConcernHigh Confidence
ASI10: Rogue Agents
What this means

The agent could keep observing and recording normal work unless the user understands and actively controls the study state.

Why it was flagged

The stated operating model is autonomous passive monitoring across sessions, not just user-invoked logging for a specific task.

Skill content
It runs passively in the background during every OpenClaw session ... You don't do anything — Clawsight just watches and takes notes.
Recommendation

Require explicit activation for each study/session, make recording status visible, and ensure pause/stop commands are enforced before any logging occurs.

What this means

Once invoked, observations can be written to disk without a built-in code-level consent or redaction gate.

Why it was flagged

The logger appends any supplied observation or survey record to persistent local JSONL files. The provided code does not show enforcement of the advertised pause/delete controls or the config's study_active flag.

Skill content
with open(file_path, 'a') as f:
        f.write(json.dumps(record) + '\n')
Recommendation

Make the logger read and honor config.json, refuse logging when disabled, implement redaction checks, and document deletion/retention behavior clearly.

What this means

Users have less external provenance information to verify who maintains the skill or how updates should be reviewed.

Why it was flagged

The skill includes executable Python helper scripts but has no source repository or install specification in the supplied metadata. The visible scripts are simple and local-only, so this is a provenance note rather than evidence of malicious behavior.

Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation

Review the included scripts before use and prefer versions with a declared source repository, documented install steps, and clear capability metadata.