ClawHub
Back to skill

Security audit

Agente Literatura

Security checks for vulnerabilities and agentic risk

Overview

This is a conversation-only literature tutoring skill with slightly broad trigger wording but no hidden or high-impact behavior.

Before installing, expect this skill to steer relevant or adjacent study conversations toward literary analysis in a vivid conversational style. If you only want it used for explicit literature questions, narrow the activation wording, but no security-sensitive behavior was found.

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 activation rule is genuinely overbroad: it triggers not only when Antonio mentions literature-related topics, but also whenever the orchestrator merely detects an 'opportunity de conexão com Literatura.' That subjective criterion can cause the skill to be invoked outside its intended scope, leading to misrouting, prompt-surface expansion, and interference with more appropriate domain skills. In this context the content is not directly malicious, but ambiguous routing logic in agent systems is a real security and reliability risk because it increases unintended activation paths.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.