Back to skill

Security audit

boyue

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only governance skill that guides software planning decisions and does not request privileged access, persistence, or data movement.

Installers should treat this as a planning and review aid, not an execution tool. It may add process overhead on larger or harder-to-reverse changes, but its own artifacts do not introduce code execution, credential handling, persistence, or hidden behavior.

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

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The document introduces 'Trigger conditions' and says to 'Run an Ownership check before introducing durable complexity,' but it does not define a precise invocation phrase, scope boundary, or negative examples. This could lead to inconsistent or overly broad activation because 'durable complexity' is interpretive and the skill does not clearly state when it should not be used.

Content

No source excerpt is available for this finding.