Security audit

research Decision

Security checks for vulnerabilities and agentic risk

Overview

This skill is a research helper that asks the agent to verify information with sources and local version checks; its behavior is coherent, but users should be aware it may run local inspection commands and perform web searches.

Before installing, understand that this skill is meant to research online and may run local version or dependency checks during troubleshooting. Use it on repositories where that inspection is acceptable, and avoid sending private error logs, package names, or proprietary context into web searches unless you explicitly want that included.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (6)

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill explicitly directs the agent to run local commands such as version and dependency checks before responding, but it does not require user consent, scope limitation, or warning that local system state will be inspected. In a real agent environment, this can expose sensitive workspace details, installed software, internal package names, or environment characteristics beyond what the user intended to share.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill encourages online research and fetching documentation from external sources without warning that prompts, error strings, package names, versions, or other context may be transmitted to third-party services. This creates a data exposure risk, especially when troubleshooting private systems, proprietary stacks, or incident-related details.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file's instructional content is written in Chinese and explicitly separates search directions into Chinese and English, but the overall skill does not offer a user language choice or document a justified locale restriction. Under the policy, forcing a specific language or locale without opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The description says the skill should prioritize bilingual Chinese and English retrieval by default. This imposes a language behavior without indicating that the user can choose or opt out, which matches the language/locale policy concern.

Natural-Language Policy Violations

Low

Confidence: 96% confidence
Finding: This line makes bilingual searching mandatory regardless of user preference or context. Because no language choice or opt-in is provided, it creates a natural-language policy issue around forced locale/language behavior.

Natural-Language Policy Violations

Low

Confidence: 94% confidence
Finding: The instruction says to flexibly combine Chinese and English queries and presents all query patterns in those two languages only. This imposes a specific language/locale behavior without any opt-in or alternative for users who may prefer another language.

Static analysis

No suspicious patterns detected.