ClawHub
Back to skill

Security audit

Stoic Quotes

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides Stoic quotes from bundled Markdown files, with a minor chance of activating on broad inspiration requests.

Installers should be aware that the skill may answer some general inspiration or quote requests with Stoic quotes. It does not request sensitive access or perform system actions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough to match common requests for general inspiration or guidance, which can cause the skill to activate when the user did not specifically want a Stoic quote workflow. This is a genuine scope/activation weakness, though the skill’s content is low-risk and limited to quotes, so the main danger is unintended invocation or response hijacking rather than direct security harm.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The 'When to Use' examples include ambiguous phrases like 'Quote of the day' and broad theme-based requests without hard boundaries, making accidental triggering plausible in ordinary conversation. In this skill’s context the impact is limited because it only serves quotes, but it still weakens routing precision and could override a more appropriate skill or default assistant behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.