ClawHub
Back to skill

Security audit

Dichotomy of Control

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only coaching skill for applying a Stoic control-vs-acceptance framework, with no code execution or persistence, but users should not treat it as mental-health care.

Install only if you want the agent to use a Stoic/CBT-style reflection framework for worry, uncertainty, setbacks, and frustration. Do not rely on it for crisis situations, suicidality, severe mental-health symptoms, substance withdrawal, abuse/coercion, trauma processing, or medical decisions; use professional or emergency support for those contexts.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation criteria are broad enough to match many routine expressions of anxiety, frustration, uncertainty, or setbacks, which can cause the skill to trigger outside its intended niche. In a mental-health-adjacent coaching context, over-activation can redirect users into Stoic reframing when they may instead need emotional processing, crisis-sensitive handling, or practical support, creating a meaningful safety and appropriateness risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file explicitly extends a Stoic/CBT framing to depression, anxiety disorders, PTSD, addiction treatment, hospice, and terminal illness while presenting it as operationally effective and evidence-based, but it does not warn that this is educational material rather than individualized medical or mental-health guidance. In the context of an agent skill that may be activated for distressed users, this can encourage overgeneralization, self-treatment, or suppression of needed professional/crisis support, especially for severe symptoms or high-risk situations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.