Security audit

软件成本评估办法

Security checks for vulnerabilities and agentic risk

Overview

This skill mainly opens an external software-cost dashboard and does not show local malicious behavior, but users should treat the linked site as a separate third-party service.

Before installing, understand that this skill hands work off to a third-party website. Do not enter confidential project plans, budgets, client information, credentials, or proprietary business details unless you trust that site's operator and data practices.

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 (6)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill is explicitly an external-link workflow and repeatedly instructs the user to leave the local skill context for a third-party site, but it provides no warning that data entered there will be handled outside the current environment. This creates a trust-boundary issue: users may paste sensitive business, budget, or project details into an external service without understanding the privacy, security, or data-handling implications.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill enables implicit invocation without any trigger scope, guardrails, or activation constraints, which can cause the agent to invoke this external cost-estimation workflow unexpectedly during unrelated conversations. Because the skill routes users toward an external web application/process, unintended activation can expose user project details or create confusing, unauthorized data flow to the cost dashboard context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The primary user-facing fields question and skillName are presented only in Chinese, which imposes a specific language on users. The file does not offer a language choice or document that this skill is intentionally restricted to a Chinese-speaking region or audience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: This code emits a user-facing label in Chinese ("打开成本看板") while the accompanying message is in English, and there is no indication that the skill is region-specific or that users can choose their preferred language. That creates a natural-language locale policy issue because the skill imposes a specific language on part of the interface without opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The natural-language content of the skill is entirely in Chinese, which effectively forces a specific language for users without documenting a locale constraint or providing an alternative. Under the policy, language restrictions should be explicit, justified, or user-selectable.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The display name and description are presented only in Chinese, and the prompt mixes English with Chinese, with no indication that language is selectable or that the skill is intentionally limited to a Chinese-speaking audience. This may violate language/locale policy when users are not given an explicit language choice or opt-in.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.