Openclaw Workspace Pro
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
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.
The one-command installer may fail or leave only partial setup completed, especially before creating the promised .gitignore and .env files.
The install script depends on template files that are not listed in the supplied file manifest, which lists only templates/AGENTS-additions.md, templates/MEMORY-COMPACTION.md, and templates/TOOLS-additions.md.
cp "$SKILL_DIR/templates/gitignore" "$WORKSPACE_DIR/.gitignore" ... cp "$SKILL_DIR/templates/env.example" "$WORKSPACE_DIR/.env"
Verify the package includes templates/gitignore and templates/env.example before installing, or create/review those files manually.
Future agent runs may access the listed services without asking first, which could be broader than some users want.
The skill installs guidance that pre-approves network access to several domains and service classes. This is disclosed as a network security allowlist, but it affects future agent tool-use decisions.
**Only access these domains without asking first:** - `*.googleapis.com`, `oauth2.googleapis.com` ... - `api.telegram.org` ... - Standard package managers
Review and narrow the allowlist in TOOLS.md after installation, especially messaging services and package-manager access.
The workspace may contain API keys or tokens that future agents and scripts can use.
The skill expects users to place service credentials in a local .env file. This is appropriate for the stated secrets-management purpose and no artifact shows credential leakage.
After installation, populate `.env`: # Example: YouTube API YOUTUBE_API_KEY=your_key_here YOUTUBE_OAUTH_CLIENT_ID=your_id_here # Example: Task Management VIKUNJA_API_TOKEN=your_token_here
Only add credentials you intend the workspace agent to use, keep .env out of version control, and scope tokens to the minimum needed permissions.
Long-term memory files may preserve sensitive context, while old raw logs may be deleted after summary.
The skill creates a persistent memory workflow that summarizes, archives, and deletes older logs. This is central to the stated memory-compaction purpose but affects retention and reuse of workspace context.
Update MEMORY.md with distilled insights ... Create monthly summary in `memory/archive/` ... Delete raw daily logs >30 days (after archival confirmation)
Review MEMORY-COMPACTION.md before following it, exclude sensitive data from long-term summaries, and confirm backups or retention needs before deleting logs.
The skill's workflow rules can continue influencing future agent sessions until removed or edited.
The installer persistently modifies workspace-level agent guidance. This is disclosed and backed up, but it changes future agent behavior beyond a single invocation.
cat "$SKILL_DIR/templates/AGENTS-additions.md" >> "$WORKSPACE_DIR/AGENTS.md" ... cat "$SKILL_DIR/templates/TOOLS-additions.md" >> "$WORKSPACE_DIR/TOOLS.md"
Review the appended AGENTS.md and TOOLS.md sections after installation and keep the generated backups so you can revert if needed.