ClawHub
Back to skill

Security audit

Prospect

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives structured prospect-prioritization advice and does not request execution, credentials, persistence, or external access.

Installers should expect this skill to analyze business target lists supplied by the user and return prioritization advice. Use care with private customer or prospect data, and confirm intent if a generic phrase such as 'who should I target' could mean something outside sales, partnerships, or business development.

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 (2)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger phrase set includes broadly worded business-language activators such as 'who should I target', which can match ordinary conversation outside a clearly scoped prospect-evaluation workflow. In an agent environment, overly broad triggers can cause unintended activation of this skill, leading to misrouting of user intent, unexpected processing of business data, or interference with other skills.

Vague Triggers

Low
Confidence
83% confidence
Finding
The trigger list provides no explicit activation boundaries, exclusions, or negative examples, so the runtime may invoke the skill for loosely related business requests. While this file contains no code execution or direct data exfiltration behavior, ambiguous activation increases the chance of accidental use on the wrong input or workflow.

Static analysis

No suspicious patterns detected.