Back to skill

Security audit

Leadership Influence Planner V2

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only leadership coaching framework with disclosed ethical boundaries and no code, data access, persistence, or privileged behavior.

Installers should understand that this skill may be invoked for leadership or workplace conversation-loop advice and will shape responses using an influence framework. It does not run code or access data, but users should still apply judgment for HR, legal, safety, harassment, or mental-health situations, where the skill itself says to prioritize professional support and boundaries.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
- For gotcha loops, acknowledge the concrete issue without accepting punishment theatre.
   - For helplessness loops, stop solution-chasing and ask what experiment they will own.
   - For courtroom loops, refuse the judge/audience role and move to agreements.
   - For passive resistance, clarify the commitment and consequence without moralizing.

5. **Choose Baker mode after the loop is interrupted**
   - Facts barrier -> Investigation.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The default prompt uses a broad natural-language trigger phrase ('diagnose the conversation loop and choose an ethical leadership influence move') that can plausibly match ordinary user requests about workplace conversations or leadership advice. Because implicit invocation is enabled, the skill may be selected unintentionally in contexts where the user did not explicitly request this planner, creating prompt-routing ambiguity and unexpected influence-oriented behavior.

Content

No source excerpt is available for this finding.