Back to skill

Security audit

Herzberg Two-Factor Theory

Security checks for vulnerabilities and agentic risk

Overview

This skill provides employee-motivation coaching without requesting account access, executable software, or automatic workplace changes.

Use authorized, anonymized or aggregated employee feedback. Exclude confidential interview details and identifiers, including from any saved lessons, and review recommendations before changing workplace policies.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow instructs collection of employee interview and survey feedback without privacy or confidentiality warnings.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

Exit interviews, stay interviews, and 1:1 feedback can contain identifiable complaints and sensitive employment information. The skill directs collection and classification of this information without warning users to protect confidentiality or minimize personal data supplied to the agent.

Content

No source excerpt is available for this finding.