ClawHub
Back to skill

Security audit

Stress Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only stress-relief guidance skill with clear safety boundaries and no executable, storage, network, or persistence behavior.

This skill is appropriate for everyday stress and grounding support. It should not be treated as therapy, diagnosis, emergency help, or crisis monitoring; users describing immediate danger or self-harm should be directed to local emergency services or a trusted person nearby.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
- Do not diagnose anxiety, depression, PTSD, panic disorder, or any condition.
- Do not promise crisis detection or safety monitoring.
- Do not ask the user to disclose sensitive trauma details.
- Do not tell a user they are safe when they describe immediate danger.
- Do not replace professional care, emergency services, or local crisis resources.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file is primarily written in English, but Scenario 4 switches to Chinese and provides a Chinese-only user input and expected output. This creates a locale/language policy concern because the skill introduces a specific language variant without stating that language is optional or user-selected.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.