ClawHub
Back to skill

Security audit

tcms-performance-analyst

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed monthly content analytics helper that reads specified content data and writes an advisory report without hidden execution or privileged behavior.

Before installing, users should know this skill may generate weaker product-line analysis if the product map is missing; provide the product_line_map when accuracy matters and review the generated report before acting on recommendations.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The skill’s hard rules require product-line analysis to use the private product map and prohibit inference from titles, but the failure-handling section later permits title-based inference when the product map is missing. This contradiction can cause the agent to fall back to weaker, potentially incorrect classification logic and may expose sensitive internal taxonomy assumptions or produce misleading business reports despite earlier safety constraints.

Static analysis

No suspicious patterns detected.