ClawHub
Back to skill

Security audit

Clawhub Skill Compliance

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only publishing checklist that encourages clearer metadata and safer package references, with no hidden execution or persistence behavior found.

This skill is appropriate as a compliance checklist. Users should treat its command snippets and placeholders as examples to adapt carefully, not as instructions to install arbitrary packages without normal package verification.

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 100)May include surrounding context.

md
| Check | Fix |
|-------|-----|
| Using remote execution? | Prefer global install |
| Using `npx -y`? | Remove (no verification bypass) |

**Safe pattern**: Verify package, install globally, use binary name.

Static analysis

No suspicious patterns detected.