ClawHub
Back to skill

Security audit

Model Resource Profiler

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local profiler-report helper that reads user-supplied JSON trace files and writes reports, with no evidence of hidden network, persistence, or destructive behavior.

Install this only for profiler artifacts you trust and provide explicit input and output paths, preferably writing reports to a temporary or project-local directory. Do not use it on pickle snapshots; export JSON from your own trusted training environment as the skill recommends.

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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs reading user-provided local profiler artifacts and writing report outputs, but it does not declare any explicit tool scope or permissions. That omission weakens least-privilege controls and can allow broader-than-intended file read/write behavior at runtime, especially if an agent interprets paths too permissively or accesses unintended local files.

Static analysis

No suspicious patterns detected.