ClawHub
Back to skill

Security audit

Kungfu IFS Companion

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed non-clinical companion-writing guide with no executable code, persistence, credential use, or hidden data access.

Install this only if you want the agent to sometimes answer in a warm, IFS-inspired companion style for emotional-support or companion-copy tasks. It is not a therapist or crisis service, and users should rely on real-world emergency, clinical, or trusted personal support for safety-critical situations.

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
87% confidence
Finding
The activation description is very broad and overlaps with routine conversation, emotional support, copywriting, and agent-behavior requests. That can cause unintended invocation in normal chats, allowing the skill to steer responses into a specialized companion mode even when the user did not explicitly ask for it, which weakens predictability and can be riskier in sensitive mental-wellness contexts.

Static analysis

No suspicious patterns detected.