ClawHub
Back to skill

Security audit

1Person Pro

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple connector description for an external AI-assistant service, with disclosed API-key setup and no bundled executable code.

Before installing, review 1Person Pro's documentation and privacy terms so you understand what task data may be sent to the service, what memory is retained, and what controls exist for autonomous workflows. Treat ONEPERSON_API_KEY like any other credential.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill is described in very broad terms such as multi-agent orchestration, autonomous workflow execution, and persistent memory, but it does not define clear trigger boundaries, scope limits, or exclusion conditions. In an agent ecosystem, this can cause over-invocation or misuse in sensitive contexts, increasing the chance that the skill is used for actions involving user data, external systems, or delegated automation without sufficient guardrails.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description advertises autonomous workflows and persistent memory but omits any user-facing warning that the skill may retain context across sessions or perform actions that affect tasks and connected systems. This creates a consent and transparency gap: users may provide sensitive information or enable workflows without understanding that data may persist or that automation may continue beyond a single prompt.

Static analysis

No suspicious patterns detected.