Hybrid training plan

• Outcome: Pass
• Latest audit: May 28, 2026 at 10:34 AM UTC
• Version:
  1.0.1

Overview

This skill is a disclosed Hybrid Training Plan account integration that reads and updates workout data using a user-provided API key.

Install this only if you want an agent to access your Hybrid Training Plan account. Use a dedicated revocable API key, keep HYBRID_API_URL at the default unless you trust another server, and confirm dates, plan IDs, session IDs, weights, and log details before asking the agent to modify your plan.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 85% confidence
• Finding: The skill invokes shell commands (`scripts/htp.sh`, `curl`, `jq`) and performs live API operations, but it does not declare explicit permissions or capability boundaries. This weakens the trust model for agents and users, increasing the chance that the skill executes account-affecting actions without appropriate review or sandboxing.

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The skill is described as helping users view and manage training plans and workout logs, but the bundled API reference also exposes API key lifecycle endpoints. That unnecessarily expands the reachable capability set into credential management, which is sensitive and not required for the stated user task; in an agent setting, this increases the chance of secret creation, disclosure, or revocation through prompt abuse or tool misuse.

Vague Triggers

Medium

• Confidence: 79% confidence
• Finding: The activation text is broad enough to match many normal fitness conversations, such as general training questions or workout logging requests, without clearly distinguishing between informational help and actions on a real account. In context, that makes accidental invocation more likely and could lead to unintended reads or writes against the user's training data.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill documents multiple authenticated, state-changing operations against a remote service, including logging sessions, completing or skipping days, and updating 1RMs, but it does not warn that data will be transmitted to hybridtrainingplan.app or that these actions modify the user's account. In this context, the omission is more dangerous because the service stores personal training history and the commands can permanently alter records.

VirusTotal

66/66 vendors flagged this skill as clean.