Back to skill

Security audit

Leadership Influence Planner

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent leadership coaching skill that gives ethical influence-planning advice and does not request file, network, credential, persistence, or execution authority.

Before installing, understand that this skill may be selected automatically for leadership or persuasion-related prompts. Its content is advisory and includes ethical guardrails, but users should still review suggested influence language for fairness, consent, and workplace appropriateness.

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
95% confidence
Finding

The skill enables implicit invocation without any visible trigger constraints or scoping, which can cause the agent to auto-select this skill in situations broader than intended. Because this skill influences leadership strategy and persuasive behavior, unintended activation could shape user-facing advice or decision-making without clear user intent or transparency.

Content

No source excerpt is available for this finding.