ClawHub
Back to skill

Security audit

Codon

Security checks for vulnerabilities and agentic risk

Overview

Codon is a simple workspace memory organizer that writes local markdown folders as disclosed, with no evidence of hidden network access, credential use, or system-level persistence.

Install only in workspaces where you want durable markdown memory files. Review what gets written under MEMORY, consider adding it to .gitignore for private notes, and avoid storing secrets or sensitive client data unless that workspace is protected.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documentation states that Codon creates a MEMORY/ directory in the workspace, but it does not prominently warn that the skill performs write operations or that repeated use may create persistent files. In agent workflows, insufficient disclosure about filesystem writes can lead to unexpected persistence, workspace pollution, or accidental inclusion of sensitive notes in synced repositories.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README tells users to trigger the skill with a very broad phrase, 'Initialize your memory system,' without clarifying scope, confirmation requirements, or where writes will occur. In an agent setting, vague invocation guidance can cause the skill to run in unintended contexts and create or modify files in the workspace without the user clearly understanding the side effects.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.