Caveat verdict
venice-admin
Venice AI account administration (balance, usage, API keys) using the user's own Admin API key against venice.ai endpoints only.
⚠ 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 (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="your_admin_api_key_here
Python chr() concatenation — builds strings to evade detection
scripts/usage.py · prose · downgraded · chr(34)+chr(34)
Python os.environ.get — reads environment variable
scripts/api_keys_list.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.