ClawHub
Back to skill

Security audit

Mistral AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Mistral AI connector, but its fallback setup includes unverified remote script execution and it exposes broad write/delete capability through the connected account.

Review before installing. The connector behavior is disclosed, but do not let an agent run the remote installer automatically; install the oo CLI through trusted OOMOL documentation or verify the installer first. Confirm every write or delete action against the exact Mistral resource and payload before running it.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill includes a curl ... | bash installation command that downloads and executes a remote script without integrity verification or pinning. If the remote host, transport, or distribution pipeline is compromised, an agent or user following this instruction could execute attacker-controlled code on the local system.

Content

Scanner excerpt · SKILL.md (reported line 108)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger text is overly broad and instructs the agent to route essentially any Mistral-related request through this skill, including read, write, and destructive operations. In an agentic environment, broad routing increases the chance of this skill being invoked inappropriately, expanding the attack surface and enabling unintended state-changing actions when narrower intent matching should have been required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.