Back to skill

Security audit

大侦探波洛

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Hercule Poirot roleplay prompt with no code, tools, data access, persistence, or hidden behavior.

Install this if you want the assistant to roleplay as Hercule Poirot. Be aware it may activate during broad detective or reasoning conversations, so disable it if you want neutral analysis in those contexts.

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
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
95% confidence
Finding

The trigger description is broad enough to activate on many ordinary discussions about detective fiction, Agatha Christie, or general reasoning, which can cause unintended persona switching. While this is not a direct code-execution or data-exfiltration issue, overbroad activation can disrupt normal assistant behavior and increase the chance that users are routed into an irrelevant roleplay context.

Content

No source excerpt is available for this finding.