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: 385453 stars.
  • Fork activity suggests reuse: 81021 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
  • /Users/steipete/openclaw
  • /Users/steipete/openclaw/dist/OpenClaw.app/Contents/MacOS/OpenClaw
  • gh workflow run full-release-validation.yml --repo openclaw/openclaw --ref main -f ref=<exact-main-sha> -f provider=openai -f mode=both -f release_profile=full -f rerun_group=all
  • node .agents/skills/openclaw-live-updater/scripts/update-main.mjs
  • pnpm openclaw
  • ~/.openclaw/runtime/gateway-<sha>

URLs

None detected in SKILL.md text scan.

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
529b5eeb5778f012bd132294ca8957894b92cf05
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

…ale output before dispatching the stop. Every external phase has a wall-clock budget: Git fetch 5 minutes, Git merge 2 minutes, dependency install 15 minutes, Gateway build 20 minutes,…

shell_command

…te/openclaw` 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, D

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.