ClawHub
Back to skill

Security audit

trainedby.ai MCP

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed trainedby.ai coaching integration for health and fitness timeline data, with privacy-sensitive access but no hidden code or local persistence.

Install only if you are comfortable connecting your trainedby.ai account and letting the agent read coaching, health, fitness, goals, reflections, and timeline summaries from that service. Review requests before saving notes, and use explicit wording when you do or do not want the trainedby.ai integration involved.

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

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The description encourages use for health data and coaching tasks but does not warn that sensitive personal health and fitness information may be accessed, summarized, or stored. In a health-related skill, this omission increases the risk that users will unknowingly trigger retrieval or persistence of sensitive data without informed consent, especially when combined with proactive note-saving guidance.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are broad enough to match ordinary coaching or progress-checking language, which can cause the skill to activate when the user did not clearly intend to access a health-coaching integration. In this skill’s context, unintended activation is more dangerous because it connects to a service handling sensitive fitness and health data, increasing the chance of unnecessary data access or disclosure.

Static analysis

No suspicious patterns detected.