Caveat verdict
web-access
07
The skill provides broad internet access capabilities, which could potentially be used for malicious purposes. However, there is no concrete evidence of 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. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (9)
<script> tag in markdown — potential code injection
integration/README.md · code · <script>
Pipe-to-shell pattern (curl | sh) — supply chain attack vector
cli.py · prose · downgraded · curl -fsSL https://deb.nodesource.com/setup_22.x | bash
Pipe to bash — executes piped content as shell commands
cli.py · prose · downgraded · | bash
Possible hardcoded credential
cli.py · prose · downgraded · token=" in value and
subprocess execution — runs system commands from Python
channels/bosszhipin.py · prose · downgraded · subprocess.run(
Downloads executables from external URLs
cli.py · prose · downgraded · download from https://
subprocess with shell=True — command injection vector
cli.py · prose · downgraded · subprocess.run(cmd, shell=True
apt-get install — installs system packages
cli.py · prose · downgraded · apt-get install
Python os.environ.get — reads environment variable
channels/bilibili.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
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.