ClawAudit verdict

kandinsky

45
🟠 Risky
Significant concerns — only install if you understand the risks

Accesses credentials AND makes external network calls

The skill accesses an API key but seems to handle it securely.

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.

45
security
70
transparency
90
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 makes external network calls — potential credential theft

LLM02 · ASI03

Findings (3)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · frontmatter · http://87.242.117.37

Pattern match low

Python urllib.request — network access

scripts/kandinsky.py · prose · downgraded · urllib.request

Pattern match low

Python os.environ.get — reads environment variable

scripts/kandinsky.py · prose · downgraded · os.environ.get(

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: KANDINSKY_API_KEY). Requires 2 system binaries. (1 elevated: curl).

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