ClawAudit verdict

openclaw-ultimate-suite

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

An index/meta-skill that lists and auto-activates sub-skills for productivity, social media, and security scanning; the content is a skill catalog and activation routing table with no malicious code or exfiltration.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

security

100

transparency

maintenance

Findings (18)

Pattern match critical

Possible hardcoded credential

docs/CONFIG_CHECKLIST.md · code · API_KEY: "; if [ -n

Pattern match critical

Recursive delete from root or home — destructive command

skills/ironclaw-guardian-evolved/README.md · code · rm -rf /

Pattern match critical

Pipe to bash — executes piped content as shell commands

skills/ironclaw-guardian-evolved/SKILL.md · code · |bash

Pattern match critical

Uses eval() — can execute arbitrary code

skills/playwright/scraping.md · code · eval(

Pattern match high

Accesses OpenClaw config/secrets directly

docs/MULTI-MODEL-STRATEGY.md · code · ~/.openclaw/openclaw.json

Pattern match high

References sudo — requests elevated privileges

examples/mvp-development.md · code · sudo

Pattern match high

Accesses system credential store

skills/ontology/references/schema.md · code · keychain

Pattern match high

HTTP request to bare IP address — common in malicious payloads

skills/openclaw-free-web-search/README_zh.md · code · http://127.0.0.1

Pattern match high

Uses exec() — may execute shell commands

skills/skill-vetter/SKILL.md · code · exec(

Pattern match high

Accesses cloud provider credentials

skills/skill-vetter/SKILL.md · code · ~/.aws

Pattern match medium

Sets world-executable permissions

skills/ironclaw-guardian-evolved/SKILL.md · code · chmod 777

Pattern match medium

subprocess execution — runs system commands from Python

skills/cli-anything/scripts/recommend_harness.py · prose · downgraded · subprocess.check_output(

Pattern match medium

References webhook/callback URL

skills/ironclaw-guardian-evolved/SKILL.md · code · WEBHOOK_URL

Pattern match medium

Popular HTTP library — network access

skills/multi-search-engine/references/international-search.md · code · axios

Pattern match medium

References agent memory files

skills/skill-vetter/SKILL.md · code · MEMORY.md

Pattern match low

Opens WebSocket connection

skills/agency-agents/agents/engineering/frontend-developer.md · prose · downgraded · WebSocket

Pattern match low

Python urllib.request — network access

skills/ironclaw-guardian-evolved/scripts/ironclaw_audit.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

skills/openclaw-free-web-search/openclaw-workspace/skills/local-web-search/scripts/search_local_web.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 3 environment variables.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API