ClawHub
Back to skill

Security audit

test

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward document-generation helper with no install steps, executable payloads, persistence, or hidden sensitive-data behavior.

Before installing, understand that this skill may be invoked for broad document-generation tasks and may create scripts and output files when asked. Review generated document code before running it if it uses external libraries or user-provided data.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation text is generic enough that many ordinary user requests about creating reports, PDFs, slides, spreadsheets, or documents could implicitly trigger this skill without an explicit opt-in. Over-broad invocation increases the chance the agent is selected in unintended contexts, which can expand attack surface and cause unsafe tool use or unexpected file generation behavior when handling adversarial prompts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.