ClawHub
Back to skill

Security audit

sales-engineer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown sales-engineering guidance skill with broad but disclosed pre-sales and POC activities, and no hidden code or persistence.

Install only if you want an agent to assist with technical sales, demos, POCs, architecture, and related documentation. For real customer environments, production systems, security testing, data migration, or role changes, require explicit user approval and limit access to the specific prospect materials needed.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s invocation and action scope are broadly defined and include operational directives like querying context, reviewing capabilities, analyzing requirements, and implementing solutions without clear trigger boundaries or authorization constraints. In an agentic environment, this ambiguity can cause the skill to activate in overly broad sales or technical contexts and perform unintended actions, including touching sensitive prospect, architecture, or security-related information.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.