Security audit

ym-campaign-retro-next

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only campaign retrospective skill with no code, network access, persistence, or hidden data handling.

Install this if you want a Chinese-language framework for reviewing completed campaigns using data you provide. Be aware that broad phrases like “activity summary” or “activity effect” may invoke it, and users who need English or non-campaign summaries may need to clarify their preferred language and scope.

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 (5)

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger list includes broad everyday phrases such as '下次怎么改' and '活动效果', which can match many general business conversations outside a narrowly defined campaign-retro intent. Over-broad triggers can cause incorrect skill invocation, pulling user input into the wrong workflow and producing misleading analysis or exposing unrelated business context to this skill unnecessarily.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The usage guidance expands activation to ambiguous requests like '这次活动怎么样' and '写个活动总结', which lack strict scope constraints and may overlap with generic summarization or planning tasks. This increases the chance of accidental routing, causing the agent to apply a retro-analysis frame to requests that may not contain sufficient data or may belong to another skill.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The entire skill guidance is written as mandatory Chinese-language instructions, including fixed phrasing requirements such as specific labels and wording conventions. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: This markdown file contains user-facing instructional content exclusively in Chinese, starting from the title and continuing throughout the document. Under the language/locale policy rule, forcing a specific language without user opt-in or justification can be a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: This markdown file contains natural-language instructions and examples exclusively in Chinese, and there is no indication that users may choose another language or that the template is intentionally limited to a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Static analysis

No suspicious patterns detected.