Security audit

I Ching Fortune Telling 易经算命

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent fortune-telling guide, but it asks for sensitive personal, image, and household data without clear privacy warnings or minimization guidance.

Review carefully before installing. Use it only when you intentionally want a fortune-telling workflow, avoid sharing exact identity, address, face, palm, or floor-plan data unless necessary, and prefer approximate or redacted inputs. Generated HTML reports may contain submitted personal details, so treat them as private.

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 (13)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill requests highly sensitive personal data including full birth date/time/place, name, and palm photos, but provides no privacy notice, minimization guidance, retention limits, or warning about the sensitivity of biometric-like imagery. Because these details can reveal identity, enable profiling, and expose intimate personal attributes, collecting them without safeguards creates a significant privacy and misuse risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Clear face photos are highly sensitive biometric data and can directly identify a person, enable face recognition matching, and expose age or other inferred traits. In this context, collecting facial images for physiognomy without privacy safeguards, consent language, or handling restrictions materially increases user risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The activation criteria are overly broad and can match ordinary conversations about career, love, destiny, or learning, causing the skill to trigger outside clear user intent. In this context, that is risky because the skill then steers users into collecting sensitive divination inputs and generating personalized outputs without strong gating.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This template hard-codes Simplified Chinese locale, and elsewhere the skill mixes English and Chinese without indicating that users can opt into their preferred language or that the tool is intentionally region-specific.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The instruction to send an HTML report creates a secondary disclosure channel for the user's question and divination inputs, but the skill does not warn that sensitive details may be embedded in the generated file. If shared, stored, or rendered elsewhere, the report may expose personal information beyond the immediate conversation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The Ba Zi section requests exact birth date, time, location, and sometimes gender, which together are sensitive personal data that can enable profiling or identity correlation. The file provides no privacy notice, minimization guidance, retention policy, or safer alternatives, making unnecessary over-collection more likely in an interactive skill.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Requesting clear hand photos creates a biometric/privacy risk because images may contain unique identifying traits, metadata, or background details. The skill asks for these photos without warning users about privacy implications, image handling, or encouraging redaction of metadata/backgrounds.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Requesting an address or floor plan alongside residents' birth dates creates a combined household-sensitivity risk, exposing both location and personal profiling data. This combination could be misused for stalking, burglary planning, household inference, or broader privacy invasion, especially since no warning or minimization guidance is provided.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This guide instructs users to prepare and potentially share sensitive personal data and biometric-like photos, including birth date, birth time, birth location, face photos, palm photos, home address, and floor plans, but provides no privacy, minimization, storage, or consent cautions. In the context of an interactive fortune-telling skill that may collect and process this information, the omission can lead to unnecessary exposure of highly sensitive data and increase risks of profiling, doxxing, identity theft, or misuse of images and location details.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The document presents large portions of its instructions and required-information fields in Chinese while also using English headings, but it does not state that Chinese is required or offer the user a language preference. This can amount to a language-policy issue because the skill implicitly assumes comfort with a specific language without opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The document includes multiple Chinese-only labels and instructions embedded throughout an English guide, such as the numbered preparation items and several table fields, without indicating that the user can choose language or locale. This can constitute a language-policy issue because the content implicitly forces part of the interaction into a specific language without opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The Tarot process section presents operational steps primarily in Chinese (e.g. 洗牌, 切牌, 布局) in an otherwise English document, with no indication that the user can choose their preferred language. This can violate a language/locale policy requiring user opt-in for non-default language content.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The Astrology section mixes English with Chinese-only labels for required user inputs, including birth date, exact birth time, and birth location. Requiring users to interpret another language for sensitive personal-data fields without offering a language option may breach language/locale policy expectations.
Content: No source excerpt is available for this finding.