ClawHub
Back to skill

Security audit

Anxiety Relief

Security checks for vulnerabilities and agentic risk

Overview

This is a simple anxiety-relief guidance skill with no code execution, network access, or hidden privilege behavior found.

Before installing, understand that this skill provides self-guided anxiety techniques and local logging prompts, not medical care. Crisis or self-harm situations should still route to emergency or professional resources; the skill itself includes 988 and Crisis Text Line guidance.

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
  • 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
Content
### Body Scan
Progressive muscle relaxation to release tension.

1. Start at your toes. Notice any tension without judgment.
2. Move slowly up through your body: feet, legs, stomach, chest, arms, neck, head.
3. Breathe into any tight areas. Consciously relax on exhale.
4. Total time: 5-10 minutes
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.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrase set includes broad, high-frequency language such as "calm me down" and "anxiety help," which can match ordinary conversation and cause the skill to activate in contexts the user did not clearly intend. In a mental-health-oriented skill, accidental invocation is more concerning because it can insert quasi-therapeutic guidance during unrelated or higher-risk situations, potentially displacing more appropriate crisis handling.

Static analysis

No suspicious patterns detected.