ClawHub
Back to skill

Security audit

Jarvis Persona Style Calibrator 01

Security checks for vulnerabilities and agentic risk

Overview

This is a simple planning and personality-workflow skill with no code, hidden access, or persistence; its scope is broad but low risk.

Before installing, understand that this skill may be invoked for broad planning-style requests, not only narrow personality calibration. It appears safe from a security standpoint because it ships only Markdown instructions and does not add code, credentials use, persistence, or external access.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The phrase 'Use when handling personality work that needs repeatable steps, quality gates, and practical outputs' is descriptive but not specific about exact triggers, boundaries, or exclusions. Without explicit scope limits or negative examples, the skill could be invoked for a wide range of ordinary planning or writing tasks.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The example 'Use this skill to turn my messy notes into a production-ready plan' is a generic productivity request rather than a domain-specific trigger. This increases the chance of unintended invocation because similar phrasing is common in ordinary assistant interactions.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The phrase 'Run this skill and give me a risk-first action sequence with acceptance checks' describes a generic execution-planning workflow and does not clearly distinguish this skill from many other planning or QA-oriented skills. The lack of domain-specific constraints makes accidental activation more likely.

Static analysis

No suspicious patterns detected.