ClawHub
Back to skill

Security audit

Hevy

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for managing a Hevy fitness account, but it documents persistent account-changing commands and an API-key command flag without clear safety guidance.

Install only if you intend to let the agent access your Hevy fitness account. Prefer HEVY_API_KEY or a secret manager over --api-key, and require the agent to show the exact planned create/update command and get confirmation before it changes workouts, routines, exercise templates, or folders.

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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description is broad enough to trigger on essentially any Hevy-related request, including requests that may only be informational or ambiguous. Overbroad activation increases the chance the agent invokes a capability-bearing skill unnecessarily, exposing account data or enabling unintended state-changing actions in a context tied to a real user account.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation advertises account-modifying commands such as creating and updating workouts, routines, and folders without any warning that these operations change persistent user data. In an agent setting, this omission makes it more likely the tool will be used for destructive or unintended changes without explicit user awareness or confirmation.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation explicitly permits passing the Hevy API key via a command-line flag, which can expose the secret through shell history, process listings, logs, and telemetry collected by wrappers or agent tooling. In an agent skill context this is more dangerous because automated systems often capture executed commands and arguments, increasing the chance of credential leakage beyond the local shell.

Static analysis

No suspicious patterns detected.