ClawHub
Back to skill

Security audit

Captain Adam Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a broad personal life-planning skill with no executable code, hidden behavior, persistence, or privileged access requests.

Before installing, understand that this skill is intentionally broad and may invite sharing personal, family, work, shopping, or scheduling details. Use it for planning and drafting support, and avoid giving it sensitive information unless it is needed for the task.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is described as an all-in-one personal assistant spanning schedules, family matters, shopping, communications, planning, and decision support, which creates an ambiguous activation boundary. Overly broad scope can cause the agent to engage in tasks beyond the user's intended context, increasing the chance of inappropriate actions, unsafe data handling, or misuse of sensitive personal information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.