Back to skill

Security audit

why

Security checks for vulnerabilities and agentic risk

Overview

This is a static educational skill about the word “why” and does not request tools, credentials, persistence, or sensitive access.

Installers should understand that this skill is mostly a long educational reference. Its trigger text could be narrower, but it does not introduce code execution, data access, credential handling, or persistent changes.

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
88% confidence
Finding

The activation guidance is extremely broad, inviting use by 'anyone' seeking information about 'Why' without defining narrow trigger conditions, boundaries, or disallowed contexts. In agent systems, such open-ended activation can cause the skill to be selected in many unrelated conversations, increasing prompt-surface exposure and the chance that its long instructional content influences behavior where it is not appropriate.

Content

No source excerpt is available for this finding.