ClawHub
Back to skill

Security audit

Cavecrew

Security checks for vulnerabilities and agentic risk

Overview

This is a small guidance-only skill for choosing compressed subagents, with no code, persistence, credential handling, or hidden behavior found.

Installers should understand that this skill may steer suitable coding tasks to named subagents and produce terse outputs; review the broad trigger wording if accidental activation would be disruptive in your workflow.

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
96% confidence
Finding

The listed triggers include generic phrases like "use cavecrew" and especially "save context," which can overlap with ordinary conversation rather than a narrowly scoped delegation request. The file also does not provide exclusion conditions or negative examples to clarify when these phrases should not activate the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.