ClawHub
Back to skill

Security audit

AOI Council

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk decision-review template that only enumerates bundled perspective files and prints a council prompt.

This appears suitable to install for local decision-review prompting. Review any future added files under agents/, because the skill intentionally includes every Markdown file in that folder as a council perspective.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
60% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
This skill is intentionally **template-driven**:
- It **does not** post externally
- It **does not** touch wallets
- It **does not** modify system config

## Council members (bundled)
The skill auto-loads any `.md` file in `agents/`.

Static analysis

No suspicious patterns detected.