Security audit

OPC 精准定位分析

Security checks for vulnerabilities and agentic risk

Overview

This career-positioning skill is coherent, but it should be reviewed because it can collect personal career details, use web research, and save a local report without an explicit consent step.

Review this skill before installing if you use shared or synced workspaces or do not want career details used in web searches. Ask the agent to confirm before browsing and before saving a report, and avoid providing sensitive contacts, employer details, or private financial information unless needed.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger phrases are broad, generic conversational phrases like '帮我定位' and '我适合做什么', which can cause the skill to activate during ordinary discussion without clear user intent to invoke it. In this skill's context, accidental activation can lead to unsolicited collection of personal/professional background and progression into web research and report generation, making the collision risk materially harmful rather than merely inconvenient.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill mandates use of web search or research tools based on user capability information but does not warn that user details may be sent to external services or used to formulate research queries. Because the workflow collects professional history, interests, and hidden assets, external browsing can expose sensitive profile data beyond the local conversation boundary.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill instructs automatic creation of a Markdown report file by default without explicit user consent or notice at runtime. This can unexpectedly persist sensitive personal assessments, income estimates, and career data to local storage, creating privacy leakage and retention risks, especially on shared systems or synced workspaces.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The display name and short description are presented in Chinese, while the default prompt is hard-coded in English. This creates a language/locale inconsistency that may force a specific language behavior without explicit user opt-in or documented justification.

Static analysis

No suspicious patterns detected.