Back to skill

Security audit

closepilot

Security checks for vulnerabilities and agentic risk

Overview

ClosePilot is a plain Markdown sales-coaching skill with disclosed persuasion-oriented guidance and no code, persistence, credential access, or hidden data flow.

Install only if you want sales-conversation coaching. Review suggested replies before sending, avoid using it in personal or support contexts, and keep the customer interaction honest and non-pushy.

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
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
94% confidence
Finding

The invocation conditions are broad enough to trigger on many ordinary conversational scenarios such as uncertainty, silence, or not knowing how to reply. That increases the chance the skill is used in contexts beyond narrow sales assistance, causing unsolicited persuasive guidance and potentially manipulative recommendations in inappropriate conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.