ClawHub
Back to skill

Security audit

StageWhisper Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple live-call task assistant with disclosed, purpose-aligned instructions and no hidden code, persistence, or install behavior.

Before installing, confirm that StageWhisper tasks are routed only from trusted calls and that any connected tools for calendar, lookup, or notifications enforce the permissions you expect. The skill itself is instruction-only and does not add executable code or persistence.

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 skill description and activation context are broad enough that the skill could be invoked for a wide range of loosely related live-call tasks without clear boundaries or authorization checks. In this context, that increases the chance of over-triggering on ambiguous requests and performing actions on research, lookup, scheduling, or notification workflows that may touch sensitive internal data or external communications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.