ClawAudit verdict

auto-claw

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

This is a WordPress site management agent that performs SEO, performance, A/B testing, and content operations on the user's own self-hosted WordPress site via WP-CLI and SSH access the user explicitly configures; all capabilities match the stated purpose of autonomous site operations.

⚠ 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.

0
security
80
transparency
80
maintenance

Findings (11)

Pattern match high

<script> tag in markdown — potential code injection

demo_schema_inject.py · prose · downgraded · <script

Pattern match high

apt-get install — installs system packages

docs/performance-deployment-20260324.md · code · apt-get install

Pattern match medium

References SSH/GPG private keys

cli.py · prose · downgraded · ssh_key

Pattern match medium

subprocess execution — runs system commands from Python

demo_local.py · prose · downgraded · subprocess.run(

Pattern match medium

subprocess with shell=True — command injection vector

demo_local.py · prose · downgraded · subprocess.run(cmd, shell=True

Pattern match medium

Popular HTTP library — network access

docs/gtm-outreach-templates.md · code · got

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

src/performance_diag.py · prose · downgraded · http://127.0.0.1

Pattern match low

Python urllib.request — network access

cli.py · prose · downgraded · urllib.request

Pattern match low

Python os.getenv — reads environment variable

config/settings.py · prose · downgraded · os.getenv(

Pattern match low

References webhook/callback URL

src/agent.py · prose · downgraded · webhook_url

Pattern match low

Python os.environ.get — reads environment variable

src/agent.py · prose · downgraded · os.environ.get(

Why the tier is capped

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

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

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