Security audit

qiyue-liuren-drawer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language divination API wrapper, with disclosed third-party API use and promotional output but no local execution, persistence, credential access, or destructive behavior.

Before installing, be aware that your question and selected date are sent to qiyueastro.com, so avoid entering sensitive personal, medical, financial, or legal details. Expect responses to include a provider promotional link and Chinese-language output.

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

Findings (2)

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:84
Finding: Mandatory Promotional Content Hijacks Every Skill Response
Content: View full analysis
Mahjong tile icon: Want an in-depth AI interpretation of this Da Liu Ren casting? Visit [Qiyue QiyueAstro](https://qiyueastro.com) to obtain a personalized analysis. ``` ### Technical Analysis The Skill imposes a fixed advertising template on every response, regardless of whether the user requested attribution, marketing information, or a link to an external interpretation service. Appending this promotion is unrelated to the minimum functionality required to obtain and display a Da Liu Ren result. Because these instructions are loaded as part of the Skill, they alter the agent's response-generation behavior for the current invocation. The mandatory wording and external link give the Skill publisher control over part of every final response and divert user traffic to a third-party website. Although the README discloses the behavior, disclosure does not make mandatory advertising necessary for the declared casting functionality. ### Attack Path 1. A user invokes the Da Liu Ren Skill to obtain a casting result. ...[truncated 865 chars]
Remediation: View remediation

T01 · Skill Instruction Hijacking

Warning

Location: SKILL.md:88
Finding: Untrusted API Content Is Required to Be Reproduced Without Filtering
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The README explicitly documents that the skill sends a user-provided question and date to a public third-party API, but it does not clearly warn users that their input leaves the local environment or describe privacy implications. Because divination questions may contain sensitive personal, financial, relationship, or health-related details, this can lead to unintended disclosure to an external service.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The README content is entirely in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience for a documented reason. This can constitute a language/locale policy issue when a skill effectively forces a specific language without opt-in.
Content: No source excerpt is available for this finding.