ClawHub
Back to skill

Security audit

Sales Playbook

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed B2B sales playbook made of Markdown guidance, with no code or hidden system access found.

Before installing, consider that sales workflows can involve confidential customer, pipeline, forecast, and call-note data. Use the skill for intentional sales tasks and avoid sharing sensitive business data unless appropriate for your workspace.

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
Confidence
95% confidence
Finding
The skill defines very broad activation phrases such as "Build my ICP", "Review my pipeline", and "Forecast this quarter" that can easily overlap with ordinary user requests in a general assistant context. If the platform uses loose intent matching, the skill may trigger unexpectedly, causing context switching, unintended processing of sensitive business data, or override of the assistant's normal behavior for unrelated queries.

Static analysis

No suspicious patterns detected.