Caveat verdict

CSVBrain Natural Language Data Queries

csv-brain

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Reads user-supplied CSV files and queries them using the user's own AI provider keys (Anthropic, OpenAI, or local Ollama); all credential access is limited to user-held keys for the intended AI backend calls.

⚠ 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.

33
security
70
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (3)

Pattern match critical

Possible hardcoded credential

SKILL.md · frontmatter · API_KEY: "Optional - for Anthropic/Claude models

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://192.168.1.100

Pattern match low

Node http/https module — low-level network access

src/csv-brain.js · prose · downgraded · require('https')

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_access

Is this flag fair?

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