Caveat verdict
cadstack
CAD automation skill that generates, validates, and executes CAD scripts for FreeCAD/AutoCAD/SolidWorks — behavior matches stated purpose with explicit safety review step before execution.
⚠ 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
agent_memory
Findings (8)
Accesses shell history/config
skills/cad-config.md · code · ~/.zshrc
References sudo — requests elevated privileges
skills/cad-config.md · code · sudo
Downloads executables from external URLs
skills/cad-config.md · code · Download from https://
<script> tag in markdown — potential code injection
skills/cad.md · prose · downgraded · <script>
Uses exec() — may execute shell commands
lib/cad_executor.py · prose · downgraded · exec(
Popular HTTP library — network access
skills/cad-qa.md · code · got
Instructs covert action — may act without user awareness
skills/cad-qa.md · prose · downgraded · silently
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
agent_memory Is this flag fair?
Thanks — recorded.