ClawHub
Back to skill

Security audit

BTC Bottom Signals

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed BTC market-analysis helper that uses AgentKey for live crypto data and does not show hidden execution, persistence, or destructive behavior.

Install this only if you are comfortable connecting AgentKey as a third-party live crypto data provider. Use OAuth where possible, review AgentKey costs before standard or deep reports, and treat outputs as research rather than financial advice.

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 (3)

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 21)May include surrounding context.

md
2. If any tool is missing, stop immediately. Do not answer from stale knowledge or another data provider.
3. Tell the user this skill requires AgentKey MCP and guide them to connect it in Hermes:
   - Transport: HTTP
   - URL: `https://api.agentkey.app/v1/mcp`
   - Auth: prefer OAuth; if Hermes does not support OAuth, use an AgentKey API key from `https://console.agentkey.app/`.
4. Ask the user to complete the AgentKey connection and retry the request. Do not continue in the same turn unless the AgentKey tools become visible.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

The skill is configured to send data to an external service over streamable HTTP at api.agentkey.app. Even if the endpoint is legitimate, this creates a trust boundary crossing where user prompts, conversation context, or derived metadata may be transmitted to a third party, which is especially concerning when combined with implicit invocation.

Content

Scanner excerpt · agents/openai.yaml (reported line 11)May include surrounding context.

yaml
value: "agentkey"
      description: "AgentKey MCP for live crypto market, sentiment, and on-chain data"
      transport: "streamable_http"
      url: "https://api.agentkey.app/v1/mcp"
policy:
  allow_implicit_invocation: true

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without any visible trigger constraints, so it may activate automatically in broader contexts than intended. Because the skill connects to a live external MCP endpoint, unintended activation can cause unnecessary external calls, data disclosure through prompts or context, and user actions being influenced by an unrequested third-party data source.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.