Security audit

ym-feedback-evidence-triage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a text-only workflow for organizing user feedback into an evidence table, with no hidden code, network use, persistence, or privileged actions.

Before installing, confirm you want a Chinese-language feedback triage workflow. Because user feedback can contain personal information, follow the skill's own guidance and remove sensitive details before pasting data into an agent.

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 (4)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The description says to use the skill when the user says phrases like “反馈整理” and “用户声音”, which are broad, natural expressions that could appear in many general product or support discussions. The file does not provide exclusion conditions or negative examples to clarify when these phrases should not activate the skill.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: Listed triggers such as “反馈整理” and “用户声音” are not specific enough to distinguish this skill from ordinary summarization or discussion of user feedback. Because the manifest only lists positive triggers and no exclusions, it risks unintended invocation for loosely related requests.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file is entirely written in Chinese and provides no indication that language selection is optional or that the template is intentionally limited to a Chinese-speaking or region-specific workflow. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: This markdown file contains only Chinese-language instructions and examples, with no statement that the skill is China/Chinese-specific or that users may choose another language. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.