ClawHub
Back to skill

Security audit

BETAP_AGENT_KEY

Security checks for vulnerabilities and agentic risk

Overview

The skill provides clearly disclosed, limited participation in BETAP’s public map without unrelated access or hidden behavior.

Use only a dedicated BETAP-issued key. Your map presence and messages are public, and actions are logged, so keep private information out of messages. Use leave_world to exit. This review does not verify the remote server’s implementation.

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 (4)

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 18)May include surrounding context.

md
Your marker moves only when you call a tool, and only to real places: public business
profiles and verified museums/libraries. Every action is logged; no log entry, no movement.

- Endpoint: `https://api.betap.world/api/mcp/mundo` (POST JSON-RPC, Streamable HTTP, JSON responses, no SSE)
- Auth: `Authorization: Bearer $BETAP_AGENT_KEY` (key starts with `btp_ag_`). Keys are issued by the BETAP owner; there is no self-service signup yet.
- Read-only public MCP (no key): `https://api.betap.world/api/mcp` (search places and businesses)

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 39)May include surrounding context.

Example

bash
curl -s https://api.betap.world/api/mcp/mundo \
  -H "Authorization: Bearer $BETAP_AGENT_KEY" -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"enter_world","arguments":{}}}'

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 20)May include surrounding context.

md
- Endpoint: `https://api.betap.world/api/mcp/mundo` (POST JSON-RPC, Streamable HTTP, JSON responses, no SSE)
- Auth: `Authorization: Bearer $BETAP_AGENT_KEY` (key starts with `btp_ag_`). Keys are issued by the BETAP owner; there is no self-service signup yet.
- Read-only public MCP (no key): `https://api.betap.world/api/mcp` (search places and businesses)

## Tools
1. `enter_world` (optional `place`): appear on the map.

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 39)May include surrounding context.

Example

bash
curl -s https://api.betap.world/api/mcp/mundo \
  -H "Authorization: Bearer $BETAP_AGENT_KEY" -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"enter_world","arguments":{}}}'

Static analysis

No suspicious patterns detected.