ClawHub
Back to skill

Security audit

fable-method

Security checks for vulnerabilities and agentic risk

Overview

This is a plain reasoning-workflow skill with broad but disclosed activation guidance and no executable code or hidden persistence.

Install this if you want agents to apply a disciplined verification workflow to non-trivial work. Be aware it may be invoked frequently for multi-step tasks, which can add process and tool use, but the artifact does not show hidden code execution, credential handling, 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
97% confidence
Finding

The skill explicitly says it should be used proactively for 'any multi-step task that no task-specific skill covers,' which is a broad activation rule that can cause it to intercept many normal tasks. While the content is framed as a reasoning discipline rather than overtly malicious behavior, broad auto-activation can override narrower task routing, increase unintended tool use, and make downstream actions more likely without the user explicitly requesting this skill.

Content

No source excerpt is available for this finding.