ClawHub
Back to skill

Security audit

EveryInfra - Data, Search and AI API Router

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently connects your agent to EveryInfra, with disclosed external services and authorization requirements for paid operations.

Use this skill when you intend to use EveryInfra. Service calls can share task inputs with the provider and spend your wallet balance. Limit the key to needed products, authorize spending deliberately, and clarify the provider before using it for ambiguous requests.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The activation condition “is unsure which product fits” is not explicitly limited to EveryInfra products and could trigger on unrelated product-selection requests.

Medium
Category
Trigger Abuse
Confidence
91% confidence
Finding

The activation phrase "is unsure which product fits" is not restricted to EveryInfra, so unrelated product-selection requests could activate this vendor-specific workflow. That could steer the agent toward an unintended external service and potentially transmit task content outside the user's intended context; the explicit requirement for authorization before paid operations reduces, but does not eliminate, this risk.

Content

No source excerpt is available for this finding.

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 56)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=everyinfra 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.