ClawHub
Back to skill

Security audit

Adam Skill 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad personal planning assistant, but the artifact does not include hidden commands, code execution, persistence, credential use, or automatic external actions.

Before installing, treat this as a general personal-organization helper and avoid giving it sensitive family, financial, medical, or account details unless needed for the task. Review any drafted messages or plans yourself before sending or acting on them.

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 defines a very broad personal-assistant role covering schedules, family matters, shopping, communications, planning, and general decision support without clear boundaries, triggers, or excluded actions. This can cause overreach into sensitive domains and increase the chance the agent is invoked for actions or advice beyond the author’s intended scope, especially where personal data, communications, or high-impact life decisions are involved.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.