ClawHub
Back to skill

Security audit

agent4.io

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed agent4.io administration helper that uses a user-provided API key to manage that tenant's agents and knowledge bases.

Install this only if you intend your agent to administer an agent4.io tenant. Expect tenant data you provide, including knowledge-base material and configuration, to be sent to agent4.io. Keep the API key restricted and revoke it if no longer needed, and confirm before using REST or other state-changing actions.

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 (9)

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 35)May include surrounding context.

md
The tools live on a remote MCP endpoint. Add it to your agent, authenticating with your tenant API key
(set `AGENT4_API_KEY`; get a key from **console → Settings → Security**, shown once at creation):

- **URL:** `https://api.agent4.io/v1/mcp`
- **Header:** `X-API-Key: $AGENT4_API_KEY`
- **Transport:** streamable-http

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 42)May include surrounding context.

md
The tools live on a remote MCP endpoint. Add it to your agent, authenticating with your tenant API key
(set `AGENT4_API_KEY`; get a key from **console → Settings → Security**, shown once at creation):

- **URL:** `https://api.agent4.io/v1/mcp`
- **Header:** `X-API-Key: $AGENT4_API_KEY`
- **Transport:** streamable-http

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 274)May include surrounding context.

md
The tools live on a remote MCP endpoint. Add it to your agent, authenticating with your tenant API key
(set `AGENT4_API_KEY`; get a key from **console → Settings → Security**, shown once at creation):

- **URL:** `https://api.agent4.io/v1/mcp`
- **Header:** `X-API-Key: $AGENT4_API_KEY`
- **Transport:** streamable-http

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 277)May include surrounding context.

md
The tools live on a remote MCP endpoint. Add it to your agent, authenticating with your tenant API key
(set `AGENT4_API_KEY`; get a key from **console → Settings → Security**, shown once at creation):

- **URL:** `https://api.agent4.io/v1/mcp`
- **Header:** `X-API-Key: $AGENT4_API_KEY`
- **Transport:** streamable-http

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 793)May include surrounding context.

md
The tools live on a remote MCP endpoint. Add it to your agent, authenticating with your tenant API key
(set `AGENT4_API_KEY`; get a key from **console → Settings → Security**, shown once at creation):

- **URL:** `https://api.agent4.io/v1/mcp`
- **Header:** `X-API-Key: $AGENT4_API_KEY`
- **Transport:** streamable-http

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill exposes a highly generic top-level invocation (/agent4-io <what you want>), which can cause the agent to route arbitrary user requests into a powerful administrative/integration skill without clear scope boundaries. Because this skill can configure agents, connect remote MCP servers, and transmit tenant data to external services, ambiguous activation increases the risk of unintended sensitive actions or overbroad delegation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 330)May include surrounding context.

agent4_agent. When you have the bot token, register them once with setMyCommands:

bash
curl -s "https://api.telegram.org/bot$BOT_TOKEN/setMyCommands" -H "Content-Type: application/json" -d '{
  "commands":[
    {"command":"agent4_agent","description":"Create a grounded agent"},
    {"command":"agent4_kb","description":"Build a knowledge base"},

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 330)May include surrounding context.

agent4_agent. When you have the bot token, register them once with setMyCommands:

bash
curl -s "https://api.telegram.org/bot$BOT_TOKEN/setMyCommands" -H "Content-Type: application/json" -d '{
  "commands":[
    {"command":"agent4_agent","description":"Create a grounded agent"},
    {"command":"agent4_kb","description":"Build a knowledge base"},

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 796)May include surrounding context.

Or by REST, with your tenant key ($BASE = https://api.agent4.io/v1):

bash
curl -X POST $BASE/mcp-servers -H "X-API-Key: $KEY" -H 'Content-Type: application/json' \
  -d '{"name":"my-tools","transport":"streamable_http",
       "config":{"url":"https://tools.example.com/mcp","headers":{"Authorization":"Bearer …"}}}'

Static analysis

No suspicious patterns detected.