ClawAudit verdict
Raon OS
zero-to-one-startup
Accesses credentials AND writes files
Korean startup companion with Agentic RAG; collects multiple LLM API keys with explicit user consent and stores them in ~/.openclaw/.env with chmod 600, matching the stated startup-advisory purpose.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
network_out
package_install
Findings (8)
Possible hardcoded credential
SKILL.md · code · API_KEY="your-api-key
<script> tag in markdown — potential code injection
clawhub-raon-os/widget/EMBED.md · code · <script
Accesses OpenClaw config/secrets directly
SKILL.md · frontmatter · ~/.openclaw/.env
References child_process — can spawn system processes
bin/raon-os.js · prose · downgraded · child_process
subprocess execution — runs system commands from Python
scripts/eval_pipeline.py · prose · downgraded · subprocess.run(
Python urllib.request — network access
clawhub-raon-os/scripts/agentic_rag.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
clawhub-raon-os/scripts/kakao_webhook.py · prose · downgraded · os.environ.get(
Popular HTTP library — network access
clawhub-raon-os/scripts/parse_unified_pdf.py · prose · downgraded · got
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
Requires 2 system binaries.
file_writepackage_installnetwork_outcredential_access Thanks — recorded.