ClawHub
Back to skill

Security audit

Self-Evolution 3D

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only coaching skill for personal growth diagnostics, with no code execution, persistence, credential use, or hidden data access.

Install only if you want the agent to provide structured personal or leadership-growth coaching. Because it may ask for self-reflection and feedback about interpersonal patterns, avoid sharing sensitive personal details you do not want processed, and use appropriate professional support for acute mental health, medical, financial, or relationship crises.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (3)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
| Domain | Height | Width | Depth |
|---|---|---|---|
| **Founder** | Interview 5 end-chain customers; rewrite mission in their before/after | Read one non-tech book; apply one concept explicitly to current org challenge | Post-meeting 3 sentences: want / did / observed in real time |
| **Executive** | Articulate who org ultimately serves; one decision/week by that constituency | Shadow an unlike-field practitioner one day; debrief in writing | Daily 5-min: emotional state, when it shifted, what triggered it |

*Contribute packs → deciqAI repository (domain + failure mode per constrained dimension + minimum viable move).*

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation criteria are broad, natural-language phrases such as 'I've been working hard but I'm not growing' and other common self-improvement statements. In an agentic system, this can cause the skill to trigger in situations where the user intended a different kind of help, leading to inappropriate coaching, misrouting, or failure to prioritize more suitable or safety-critical skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The 'When to Use' section repeats similarly open-ended triggers like leadership plateau, lack of growth, and organizational influence problems without precise invocation boundaries. This increases the chance of overbroad routing, especially because these themes overlap with therapy, career advice, performance management, and crisis contexts that may require different handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.