Back to skill

Security audit

Philosophy Dialogue Publish

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only philosophy persona skill with some broad activation wording but no code, persistence, credential use, or hidden system access.

Installers should understand that the skill may shift responses into philosopher-style roleplay when broad trigger phrases are used; use explicit phrasing when invoking it and avoid relying on persona output as factual or professional advice.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description states '输入任意人名即可激活对应视角进行对话', which implies that entering any person's name can trigger the skill. This lacks clear constraints on which names are valid and when the skill should or should not activate, increasing the risk of unintended invocation during ordinary conversation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger phrases are broad, natural-language expressions likely to appear in normal conversation, which can cause accidental or ambiguous activation of the skill. In a meta-skill that switches personas, unintended invocation can override the expected assistant behavior and route conversations into stylized roleplay when the user did not clearly request it.

Content

No source excerpt is available for this finding.