ClawAudit verdict
xinling-bushou-v2
Personality/persona management system with flattery character modules; purely local CLI tool managing persona configurations with no external data 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.
Findings (5)
<script> tag in markdown — potential code injection
test/自动化测试框架.md · code · <script>
Possible hardcoded credential
scripts/ai_corpus_upgrader.py · prose · downgraded · Token=" + api_key
Python os.getenv — reads environment variable
architecture.md · code · os.getenv(
References agent configuration files
claw-systems-research.md · prose · downgraded · CLAUDE.md
Python urllib.request — network access
scripts/ai_corpus_upgrader.py · prose · downgraded · urllib.request
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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?
Thanks — recorded.