Back to skill

Security audit

oop-dev-skill

Security checks for vulnerabilities and agentic risk

Overview

This is a plain coding-standards guide with some opinionated or broad guidance, but no hidden execution, persistence, credential use, or data access.

Install this if you want a strict, Alibaba-inspired OOP coding standards reference applied broadly to code review and generation. Review the naming and documentation preferences against your team's conventions, especially boolean fields and comment language, because the skill may push opinionated style choices.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation description is broad enough that the skill could activate for many generic engineering tasks, including code generation, architecture, tests, and schema design across many languages. Over-broad activation can cause unintended instruction injection into unrelated workflows, overriding user intent or introducing rigid rules where they were not requested.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document states that boolean fields in data objects must not be prefixed with is, giving isDeleted as a bad example. Later, it requires database boolean/flag fields to be named is_xxx, which directly conflicts when the skill is used for schema design alongside object/model design. This is an active contradiction inside the skill's own guidance, creating intent-code divergence in the documented standards.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The guidance says to prefer clear native language comments over broken English, which imposes a language choice without indicating user or team preference. This is a natural-language policy issue because it directs output/comment language behavior without offering opt-in or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.