ClawHub
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 aid with disclosed ethical boundaries and no evidence of hidden system access or unsafe behavior.

This skill appears safe to install for leadership conversation planning. Treat its outputs as coaching suggestions, not professional HR, legal, or mental-health advice, especially where abuse, retaliation, threats, harassment, or safety risks are involved.

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
Confidence
80% confidence
Finding
The default prompt activates on a general instruction to "diagnose the conversation loop and choose an ethical leadership influence move," but the manifest does not define clear trigger boundaries, exclusions, or narrower invocation constraints. This makes the activation scope somewhat ambiguous for a manifest file, increasing the chance of unintended invocation in ordinary coaching or communication contexts.

Static analysis

No suspicious patterns detected.