Back to skill

Security audit

Compensation

Security checks for vulnerabilities and agentic risk

Overview

This is a small compensation-negotiation guidance skill with no executable code, persistence, credential use, or hidden data access.

Before installing, understand that this skill may be offered for compensation-adjacent workplace planning. Use it for offer, raise, pay, and negotiation discussions, and remember it explicitly is not legal or tax advice.

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 trigger list includes broad terms like "offers," "raises," and "closely related work," plus a generic condition about preparing a "review, rollout, or stakeholder communication." These phrases are not tightly scoped to compensation-specific situations and provide no negative examples or exclusion conditions, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.