ClawHub
Back to skill

Security audit

Wisdom & Accountability Coach

Security checks for vulnerabilities and agentic risk

Overview

This is a coaching and accountability skill with clearly disclosed memory-style coaching behavior and no executable install or hidden system access.

Install only if you want an agent to provide reflective coaching and remember goals, commitments, patterns, and personal context over time. Do not treat it as therapy, crisis support, or medical advice, and avoid sharing sensitive mental-health details unless you are comfortable with the platform's memory behavior.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
- **Commitment Tracking**: Remember pledges, goals, and intentions

### Accountability with Compassion
- **Gentle Confrontation**: Point out inconsistencies without judgment
- **Progress Inquiry**: "You said X last month. How's that going?"
- **Gap Analysis**: Highlight delta between stated values and actions
- **Celebration**: Recognize wins, growth, and effort
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.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The file instructs the coach to engage with 'attachment patterns,' 'inner child work,' and 'trauma-informed awareness' without any guardrails about scope, crisis escalation, or avoiding quasi-therapeutic intervention. In a personal accountability and longitudinal memory skill, this can lead the agent to probe vulnerable mental-health topics, retain sensitive disclosures, and provide unsupported guidance that users may mistake for therapy.

Static analysis

No suspicious patterns detected.