ClawHub
Back to skill

Security audit

Contract Reviewer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward contract-review checklist that analyzes user-provided agreements and does not install code, persist data, or take actions on the user's behalf.

Install only if you are comfortable sharing contract text with the agent environment you use. Treat the output as issue spotting and negotiation support, not legal advice, and have counsel review important or regulated agreements.

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 60)May include surrounding context.

md
| **Data handling** | DPA included? Breach notification timeline? Data return/deletion? |
| **Non-compete / non-solicit** | Scope, duration, geography reasonable? |
| **Force majeure** | Included? Pandemic/cyber covered? |
| **Assignment** | Can they assign without consent? Change of control? |
| **Warranty disclaimers** | "As-is" without recourse? SLA commitments? |
| **Confidentiality** | Mutual? Duration? Carve-outs? Survival period? |
| **Dispute resolution** | Arbitration vs litigation? Venue favorable? |

Static analysis

No suspicious patterns detected.