Caveat verdict
brainforge-autoresearch
The skill uses dynamic_eval capability which can pose a risk if not properly sanitized, but it seems to be used for a legitimate purpose of optimizing prompts.
⚠ 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.
Findings (4)
<script> tag in markdown — potential code injection
autoresearch.py · prose · downgraded · <script
Python urllib.request — network access
autoresearch.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
autoresearch.py · prose · downgraded · os.environ.get(
Popular HTTP library — network access
autoresearch.py · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
dynamic_eval Is this flag fair?
Thanks — recorded.