ClawAudit verdict

web-llm-chat

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

The skill chats with web-based LLMs through the Chrome Relay extension, which requires package installation. However, it seems to be for a legitimate 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.

80
security
80
transparency
80
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (3)

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/qwen_chat.js · prose · downgraded · http://127.0.0.1

Pattern match low

Opens WebSocket connection

references/chrome-relay.md · prose · downgraded · WebSocket

Pattern match low

Node http/https module — low-level network access

scripts/qwen_chat.js · prose · downgraded · require('http')

Permissions & capabilities

No declared permissions — minimal attack surface.

package_install

Is this flag fair?

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