ClawHub
Back to skill

Security audit

Negative Space

Security checks for vulnerabilities and agentic risk

Overview

This skill is a reasoning aid that encourages agents to check assumptions before acting, with no executable code, persistence, or hidden data handling.

This skill is appropriate to install if you want the agent to pause and reason about missing context before substantial work. It may make the agent ask clarifying questions more often, but the artifacts do not show risky authority or hidden execution.

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
Content
What am I assuming that the user never confirmed?

Common assumption traps:
- **Platform assumption**: Assuming OS, shell, runtime, or package manager without checking
- **Location assumption**: Assuming which file, function, or module the user means
- **Intent assumption**: Assuming "fix" means "patch" when it might mean "redesign"
- **State assumption**: Assuming the codebase is clean, tests pass, or dependencies are installed
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.

Static analysis

No suspicious patterns detected.