SR
SKILLRADAR
AI Security • Benchmarking • Index
Menu
Trust Report v1

openclaw-live-updater

Maintain the canonical live OpenClaw main checkout, managed Gateway, local macOS app, exact-head main CI, and recurring full release validation. Use for fast-forward update heartbeats, post-update runtime verification, attributable CI repair and repo-native landing, or non-publis

Overall
68
Trust
47
Utility
80
Momentum
95

Install caution

High-risk behavior present

Risk: High

Source: OpenClaw Built-in Skills

Path: .agents/skills/openclaw-live-updater/SKILL.md

Review flags: filesystem/home-directory access, network access or external URLs, package installation commands, shell command snippets. These are review signals, not definitive security judgments; inspect before installing.

Required permissions

  • Shell commands
  • Network/API usage
  • Filesystem/home access

Permissions are inferred from SKILL.md text only. They are review prompts, not guarantees about runtime behavior.

Risk flags explained

filesystem_write_or_home_accessmedium

Mentions filesystem writes, deletes, home-directory paths, or config/key locations.

network_accessmedium

Mentions external URLs, network APIs, downloads, or HTTP client usage.

package_installmedium

Mentions package installation or dependency-fetching commands.

shell_commandmedium

Contains shell command snippets. Review commands before copy/paste or agent execution.

Score explanation

Trust

  • Trust starts at 90 before review-signal penalties and metadata bonuses.
  • Risk-signal penalty: -45 from 4 detected flag(s).
  • Metadata bonus: +2 from author/version/description fields.

Utility

  • Utility starts at 55 and rewards clear descriptions, runnable examples, and explicit setup needs.
  • Description present: yes.
  • Command examples detected: 9.
  • Environment variables detected: 0.

Momentum

  • Momentum starts at 45 and uses public repo activity signals.
  • Recent commit activity: latest repo update was 0 day(s) ago.
  • Recent commit volume: 100 commit(s) in the lookback window (+20).
  • Source has strong public adoption: 390331 stars.
  • Fork activity suggests reuse: 82114 forks.

Overall

  • Overall score weights trust 45%, utility 35%, and momentum 20%.

Detected signals

Env vars

None detected in SKILL.md text scan.

Commands

  • $openclaw-pr-maintainer
  • $openclaw-testing
  • $release-openclaw-ci
  • ai.openclaw.*
  • node --import tsx .agents/skills/openclaw-live-updater/scripts/update-main.mjs
  • openclaw gateway restart
  • pnpm ci:full-release -f validation_purpose=main-qualification --sha "$MAIN_SHA" --workflow-sha "$MAIN_SHA" -f provider=openai -f mode=both -f release_profile=full -f rerun_group=all
  • pnpm openclaw
  • ~/.openclaw/runtime/gateway-<sha>

URLs

  • https://github.com/openclaw/openclaw/issues/114967

Provenance & evidence

SkillRadar makes each review traceable back to the exact source path, source blob SHA, scanner version, and text-only policy that produced the report.

source
github.com/openclaw/openclaw@main
path
.agents/skills/openclaw-live-updater/SKILL.md
source blob SHA
a04733eab6d27e1e0bb94d4a86a28371c8e86d0f
scanner version
0.3.0
security model
text_only_no_execute_no_install_no_secrets
scan policy
Fetched and scored as text only; no install, no execution, no runtime loading.

Evidence snippets

filesystem_write_or_home_access

…cute either this checkout's `dist/index.js` or a clean detached canonical snapshot under `~/.openclaw/runtime/gateway-<sha>` whose commit is an ancestor of the checkout; reject every…

package_install

…ndency-input change, absent `node_modules`, or missing/invalid build provenance requires `pnpm install --frozen-lockfile`. When a build is required, do not install before acquiring the mainten…

network_access

…t` after every exit and cause a persistent restart storm, even without a plist ([#114967](https://github.com/openclaw/openclaw/issues/114967)). ## Fast Update And Maintenance 1. Run the…

shell_command

…checkout as a read-only-to-the-agent deployment mirror: clean, standalone, full, on `main`, and fast-forwarded only. Make every repair in the controlling Codex project worktree. ## Boundaries - Report only in the controlling Codex thread. Never send Slack, Di

Watch this skill

Get alerted when this skill adds credential requirements, shell commands, external domains, remote installer patterns, or risk-level changes.

Join watchlist beta

Methodology note

SkillRadar scans SKILL.md as hostile text only. It does not execute commands, install packages, or load third-party skills.