ClawHub
Back to skill

Security audit

Parfait Charts

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides a markdown template for stacked composition chart analysis and does not request sensitive access or perform actions.

Before installing, consider whether broad trigger words could make this skill activate when you only meant general composition or structure analysis. Otherwise it is a simple chart-analysis helper with no evident sensitive permissions.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger list includes generic terms like "composition" and "structure" that are broad enough to match many ordinary analysis requests unrelated to this specific chart skill. This can cause unintended invocation or routing conflicts, leading the agent to apply the wrong skill and potentially mishandle user intent or downstream workflows.

Static analysis

No suspicious patterns detected.