ClawAudit verdict

milvus

milvus-skill

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Accesses credentials AND encodes data

Legitimate Milvus vector database integration using the official pymilvus SDK; explicitly instructs the agent to ask for connection details before writing any code and never hardcode parameters.

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.

30
security
50
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND encodes data — may obfuscate stolen credentials

LLM02 · ASI03 · ASI04

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (1)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · token="<USER_TOKEN>

Permissions & capabilities

No declared permissions — minimal attack surface.

network_incredential_accessdata_encoding
Check another skill Browse the registry Auditing your own skills or configs? Use the API