ClawHub
Back to skill

Security audit

Mens Mental Health

Security checks for vulnerabilities and agentic risk

Overview

This is a simple mental-health support skill with no executable code, but one trigger phrase is broad enough that users may want it narrowed.

Before installing, consider narrowing or removing the "need to talk" trigger so the skill only activates when you clearly ask for men's mental-health support. Treat it as a reflective support aid, not a replacement for professional care or crisis help.

A.I.G

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

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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrase "need to talk" is very broad, conversational language that can match many ordinary user requests unrelated to this specific skill. In a sensitive mental-health context, overly broad activation can cause the skill to engage unexpectedly, creating routing confusion and potentially surfacing quasi-therapeutic guidance when the user did not explicitly seek this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.