Daily Workflow (开工啦)

PassAudited by VirusTotal on May 9, 2026.

Overview

Type: OpenClaw Skill Name: daily-workflow Version: 2.0.0 The 'daily-workflow' skill is a project management tool designed to maintain context across AI work sessions by managing markdown files (e.g., STATUS.md, PENDING.md) in a local 'Docs/' directory. The instructions in SKILL.md and SECURITY.md explicitly forbid recording secrets, credentials, or sensitive data, and restrict file operations to the project-local documentation folder. No indicators of data exfiltration, malicious execution, or unauthorized access were found.

Findings (0)

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 and using the skill may add or change workflow files in the current project.

Why it was flagged

The skill instructs the agent to create and modify project files. This is central to the stated workflow purpose and is limited to Docs/, but it is still file mutation the user should expect.

Skill content
Create `Docs/` if it is missing. Maintain these files: ... `Docs/STATUS.md` ... `Docs/PENDING.md` ... `Docs/SCHEDULE.md`
Recommendation

Use it in projects where Docs/ workflow notes are desired, and review generated changes before committing or sharing them.

What this means

Project notes may preserve private work details and influence future assistant behavior.

Why it was flagged

The skill intentionally creates persistent context that later sessions or another AI may rely on. This is disclosed and scoped locally, but persistent notes can carry stale, sensitive, or misleading context if not reviewed.

Skill content
Write this compressed context into `Docs/STATUS.md` ... Continue from the compressed context in `STATUS.md` and the action plan in `SCHEDULE.md`
Recommendation

Keep secrets and sensitive customer data out of Docs/ notes, periodically review the handoff files, and treat them as helpful context rather than unquestionable instructions.