ClawHub
Back to skill

Security audit

Coala Client

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward usage guide for the coala-client CLI; its MCP and skill import behavior is disclosed and user-directed, though users should only import trusted sources.

Install this only if you intend to use coala-client. Import MCP toolsets and skills only from sources you trust, review remote or zip content before loading it, and remove entries from ~/.config/coala/ if you no longer want them active.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

md
## Chat commands

- `/help`, `/exit`, `/quit`, `/clear`  
- `/tools` — list MCP tools  
- `/servers` — list connected MCP servers  
- `/skill` — list skills; `/skill <name>` — load a skill  
- `/model` — show model info

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly instructs users to import CWL toolsets and skills from remote HTTP(S), GitHub, zip, and local archive sources into persistent config directories, but it does not warn that this downloads, writes, and later loads untrusted external content. In this context, that omission is security-relevant because imported MCP servers and skills can influence later tool execution and prompt context, increasing the risk of supply-chain abuse or unsafe trust in third-party content.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.