ClawHub
Back to skill

Security audit

huo15-reasonix-bridge

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly purpose-aligned, but it can read and resume local Reasonix project/session history with overly broad triggers.

Install only if you are comfortable letting the agent inspect your local Reasonix project registry and resume prior Reasonix sessions. Prefer giving an explicit project path and session file, and avoid vague requests like continuing the last session unless you have checked which session will be loaded.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to enumerate and operate on shared local Reasonix storage, including project roots and session files, without requiring an explicit consent or sensitivity warning first. Because these paths and sessions may contain confidential project names, filesystem locations, and conversation history, an overly eager invocation could expose private local data beyond the user’s immediate intent.

Vague Triggers

Medium
Confidence
86% confidence
Finding
Triggering on generic requests like 'continue the last session' is ambiguous because it can cause the agent to resume whichever recent Reasonix session is present, including one unrelated to the current user request. In this skill, resume loads prior context from shared local storage, so an ambiguous trigger can leak or act on sensitive historical conversations without sufficiently specific authorization.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger condition for generic requests such as 'use Reasonix to do X' without specifying project scope is too broad for a skill that can inspect all desktop projects and resume existing sessions. In context, this increases the chance of the agent selecting a project/session from shared ~/.reasonix storage without explicit scoping, which can reveal sensitive project structure or cause actions in the wrong workspace.

Static analysis

No suspicious patterns detected.