Caveat verdict
AI Provider Bridge — Unified API for Anthropic/OpenAI/Google/xAI/Mistral/Ollama
ai-provider-bridge
Provides a unified JavaScript abstraction layer for calling multiple AI provider APIs using the user's own API keys read from env vars; all key usage is transparent and directed only at the documented provider endpoints.
⚠ 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.
Findings (3)
Possible hardcoded credential
SKILL.md · frontmatter · API_KEY: "Required for Anthropic/Claude models (optional if not using Anthropic)
HTTP request to bare IP address — common in malicious payloads
src/ai-bridge.js · prose · downgraded · http://127.0.0.1
Node http/https module — low-level network access
src/ai-bridge.js · prose · downgraded · require('https')
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.