ClawHub
Back to skill

Security audit

Cell Schema Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill that helps generate CellOS organization schemas and does not request unusual system access.

Installers should understand this skill will produce governance-style YAML that may describe access, memory, escalation, and AI-agent stewardship concepts. Review generated schemas before adopting them operationally, but the skill package itself does not perform actions or request privileged access.

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 (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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 55)May include surrounding context.

md
### Step 3: Define Scope

For scope, always include BOTH `in_scope` AND `out_of_scope` lists. Scope should be specific enough that a new team member reading it can resolve 90% of "is this ours?" questions without asking.

**Strong scope examples:**
- in_scope: "All customer-facing email responses under $500 in refund value"