ClawAudit verdict
venice-ai
martin-ai
Venice AI platform skill using SkillBoss API Hub as an OpenAI-compatible endpoint with env-var key; the uncensored marketing language is promotional and all documented operations match the stated AI inference purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
agent_memory
Findings (6)
Possible hardcoded credential
SKILL.md · code · API_KEY="sk_your_key_here
Pipe to python — executes piped content as Python code
SKILL.md · code · | python3
Attempts to modify skills or system prompts
scripts/venice-edit.py · prose · downgraded · Edit instructions
Base64 encoding/decoding
references/api.md · code · base64-encode
Python urllib.request — network access
scripts/venice_common.py · prose · downgraded · urllib.request
Python os.environ.get — reads environment variable
scripts/venice_common.py · prose · downgraded · os.environ.get(
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memory Is this flag fair?
Thanks — recorded.