Caveat verdict
auto-coding-v3
auto-coding-skill
This is a structured autonomous coding workflow that operates within the user's project using standard coding tools; it has explicit safety constraints (approval rules for sensitive operations, human-in-loop interrupts), and no evidence of exfiltration or 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.
Findings (6)
<script> tag in markdown — potential code injection
skills/testing.skill.md · code · <script>
Pipe to python — executes piped content as Python code
DESIGN.md · prose · downgraded · | Python
Uses spawn() — can execute external programs
README-FULL.md · prose · downgraded · spawn(
Python os.environ.get — reads environment variable
auto_coding_workflow.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
dependency_manager.py · prose · downgraded · shutil.rmtree(
Popular HTTP library — network access
scorecard_engine.py · prose · downgraded · got
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.