ClawHub
Back to skill

Security audit

Objection Handler

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown sales-coaching guide with no code, tool use, credential access, persistence, or hidden behavior.

Install this if you want lightweight sales-objection coaching. Be aware that generic phrases about what a prospect 'said' may cause the skill to answer in a sales-response format, so invoke it clearly when that is intended.

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
88% confidence
Finding
The trigger guidance at the end uses a very broad natural-language pattern: "When the user says 'They said [objection]'...". Because this overlaps with ordinary conversation, the skill could activate unintentionally during unrelated chats, causing the agent to inject sales-objection handling behavior when the user did not explicitly request it. In context this is not overtly malicious, but it can still misroute conversations, override user intent, and create confusing or inappropriate responses.

Static analysis

No suspicious patterns detected.