ClawHub
Back to skill

Security audit

mutual-consent

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only governance skill about consent boundaries, with no executable code, install hooks, credential access, persistence mechanism, or hidden data flow.

Install this only if you want an agent to apply a broad consent and boundary-checking framework to interactions. Expect it to make the agent more likely to pause, narrow scope, avoid persistence, and discuss exit or data portability, but it does not add code execution or system 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The description says to use the skill 'when shaping how a system asks, holds scope, senses friction, announces change, or lets someone leave,' which is expansive and could overlap with many ordinary interaction-design tasks. It does not provide explicit trigger phrases, exclusions, or negative examples to clarify when the skill should activate versus when it should not.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.