ClawAudit verdict
last30days-cn
last30days-skill-cn
The skill accesses external APIs and installs packages but does not show clear malicious behavior.
⚠ 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.
Permission integrity
package_install
Findings (7)
<script> tag in markdown — potential code injection
tests/test_baidu_antibot.py · prose · downgraded · <script
Instructs covert action — may act without user awareness
scripts/lib/cache.py · prose · downgraded · Silently
Python threading.Timer — deferred execution
scripts/last30days.py · prose · downgraded · threading.Timer(
Python urllib.request — network access
scripts/lib/baidu.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/lib/cache.py · prose · downgraded · os.environ.get(
References agent configuration files
TASKS.md · prose · downgraded · CLAUDE.md
Python shutil file operation — copies/moves/deletes files
tests/test_crawler_bridge.py · prose · downgraded · shutil.rmtree(
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
Requires 1 system binary.
credential_accesspackage_install Is this flag fair?
Thanks — recorded.