Source Research

PassAudited by ClawScan on May 1, 2026.

Overview

This skill is a coherent source-research note-keeping framework that creates persistent workspace files, with no evidence of hidden network access, credential use, or destructive behavior.

This appears safe for its stated purpose. Before installing, understand that it is designed to create a persistent .source-research directory in your workspace and store source lists, methods, rejection notes, and captured information there. Review those files for accuracy and sensitivity before sharing or committing them.

Findings (2)

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

Installing or using the skill may create or update files in the current project workspace.

Why it was flagged

The helper script creates a .source-research directory by copying the bundled template into the selected workspace root. This is disclosed and purpose-aligned, but it is still local workspace mutation.

Skill content
target = root / TARGET_NAME
    if target.exists():
        print(f'[OK] Already exists: {target}')
        return 0
    shutil.copytree(TEMPLATE_DIR, target)
Recommendation

Use it only in the intended workspace and review .source-research changes before committing, syncing, or sharing them.

What this means

Future agent work may be influenced by saved source lists, rejection decisions, and research notes.

Why it was flagged

The skill intentionally creates persistent source-research artifacts that future agents may rely on, which is useful but can preserve stale, biased, or sensitive notes if users do not curate them.

Skill content
leaving reusable artifacts so future agents do not repeat the same analysis
Recommendation

Periodically review saved notes, avoid storing secrets or private personal data in .source-research, and verify important conclusions before relying on them.