Security audit

Orthogonal Agent Framework

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese task-organization skill whose file-writing and memory templates are purpose-aligned, but users should be aware it may create task files in their workspace.

Install this if you want a Chinese-language planning/execution/memory/evaluation workflow. Before using it on sensitive tasks, decide where the generated task files should live and avoid recording secrets or private data in the memory template unless you intend to persist them.

A.I.G

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

SkillSpector

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 (7)

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill states that it will automatically create multiple task-management files, but it does not warn the user about filesystem writes, when they occur, or where they will be placed. In an agent framework context, implicit file creation can lead to unintended persistence of sensitive task data, workspace modification, and surprising side effects that users did not explicitly authorize.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown template is entirely written in Chinese, including headings and status labels, which implies a fixed output language for the skill. The file does not offer a language choice or explain that the skill is intentionally limited to a Chinese-speaking or region-specific context.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The template content is entirely in Chinese, including headings, field labels, and boilerplate text, which implies the skill output is expected in a specific language by default. The file does not offer a user language choice or explain a justified region-specific requirement, which matches the natural-language policy violation criteria for forced language or locale.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The template title and framework description are written exclusively in Chinese, indicating the skill output is expected in a specific language. Under the policy rules, forcing a specific language without offering user opt-in or documenting a justified locale constraint is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The natural-language description forces a specific language/locale presentation, and the rest of the skill documentation is primarily in Chinese. Under the policy, language constraints should either be optional for the user or explicitly justified as region-specific.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: This markdown file presents all instructional content in a single language, which can amount to a language/locale policy violation when no user opt-in or alternative is offered. The file does not indicate that Chinese is optional, user-selected, or required for a justified region-specific purpose.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The entire markdown template, including headings and field labels, is written only in Chinese, which implies a fixed language for generated evaluation output. The file does not mention that users may choose another language or that the Chinese locale is a documented requirement, which can violate language/locale policy expectations.

Static analysis

No suspicious patterns detected.