ClawHub
Back to skill

Security audit

Verified Task 1.0.8

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow guardrail that asks agents to verify outputs before important actions, without adding hidden execution, persistence, or credential access.

This skill is reasonable to install as a verification checklist or workflow gate. For payments, public posting, account changes, or other irreversible actions, keep a separate human approval step even when the skill returns PASS.

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 218)May include surrounding context.

md
* prevent incorrect execution
* enforce task correctness
* keep workflows on track during autonomous runs
* ensure important actions do not proceed without verification

---

Static analysis

No suspicious patterns detected.