ClawHub
Back to skill

Security audit

documentation-and-ad

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a generic documentation/ADR helper, but it asks for broad command execution and credential-related setup without clear limits or user-control details.

Review this skill before installing. Use it only for explicit documentation or ADR tasks, avoid giving it broad shell access, and do not provide API keys or let it run commands unless you can verify exactly what files, services, and commands will be used.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly claims that command execution is restricted to a whitelist, but the manifest only exposes a generic exec capability and provides no concrete enforcement mechanism, allowed-command list, or validation rules. This creates a dangerous mismatch between documented safety guarantees and actual capability exposure, increasing the risk that an agent or user assumes commands are constrained when they are not.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill describes API key configuration, file preparation, and command execution steps but does not prominently warn users about the operational and security impact of those actions. In practice, this can normalize sensitive actions without informed consent, increasing the likelihood of unsafe execution, credential misuse, filesystem changes, or unintended external calls.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger condition states the skill activates when a user needs to perform 'related operations,' which is too vague to safely scope invocation. Overbroad triggering can cause the skill to be selected in unintended contexts, and because the skill advertises file handling, API use, and command execution, accidental invocation can lead to unnecessary side effects or risky actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.