ClawHub
Back to skill

Security audit

EveryAI - OpenAI-Compatible Text API

Security checks for vulnerabilities and agentic risk

Overview

EveryAI openly sends user-requested text to EveryInfra for AI processing and includes clear limits on sharing sensitive data.

Install if you want EveryInfra to process the text you select. Share only data you authorize for external processing, keep the API key in secret settings, and restrict it to needed capabilities using the provider's available controls. [EveryInfra documentation](https://everyinfra.com/en/docs)

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
response reports `ai_topup_required`, tell the user that the account needs a top-up instead of
   retrying.

For direct OpenAI-compatible SDK use, the REST base is `https://api.everyinfra.com/api/v1`; the
plugin should still prefer MCP when its tool is available.

## Cleaning collected data

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
## Setup in OpenClaw

1. Create an API key at https://everyinfra.com/en/docs?utm_source=clawhub&utm_medium=directory&utm_campaign=listing_2026q4&utm_content=everyai and export it as `EVERYINFRA_API_KEY`. Capability discovery needs no key; paid calls do.
2. Add the remote MCP server once: `openclaw mcp add everyinfra --url https://api.everyinfra.com/mcp --transport streamable-http`, then set its `Authorization: Bearer` header to the key in Settings -> MCP (keep the key out of config literals). Check it with `openclaw mcp doctor everyinfra --probe`.
3. The live MCP tool list is the runtime truth. EveryInfra failed or empty calls are reported in the response `billing` block; read it instead of assuming.

Static analysis

No suspicious patterns detected.