ClawHub
Back to skill

Security audit

gym-load-planner

Security checks for vulnerabilities and agentic risk

Overview

This fitness planning skill is benign; it runs local workout calculations and only stores workout history when the user uses the log feature.

Before installing, understand that using log add will store workout history locally in artifact/scripts/gym_log.json. Avoid logging information you consider private on shared machines, and delete that file if you no longer want retained workout history.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding

The skill advertises command usage that appears to include logging/tracking functionality, and the static analyzer detected file-write capability, but the manifest declares no explicit tool scope such as permissions or allowed-tools. When a skill can write files without a declared boundary, an agent may invoke it with broader filesystem access than intended, creating a risk of unintended local file modification or persistence. In this fitness context the domain is benign, but the mismatch between declared scope and detected capability still makes the behavior less transparent and harder to sandbox safely.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The log feature persists workout history to a local JSON file in the skill directory without any user-facing notice that data will be stored across runs. While this is not code execution or privilege escalation, it creates an avoidable privacy issue because users may not expect lift names, dates, weights, and reps to be written to disk and remain accessible to other local users or later processes.

Content

No source excerpt is available for this finding.