Security audit

Find Love

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, consent-focused helper for creating and publishing a public dating profile, with clear approval gates before external publication.

Before installing, understand that this skill is designed to help publish public dating intent. Use a dedicated contact method, review every field carefully, and only approve publication to a registry, GitHub pull request, or static page when you are comfortable with that information being searchable and durable.

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
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: 94% confidence
Finding: The example publishes a direct email address inside a profile format explicitly intended to be searchable, which normalizes exposing personal contact data in a public dating context. Although the surrounding guidance warns against publishing contact data that should not be searchable, the concrete example contradicts that guidance and can lead users to expose personally identifiable information, increasing spam, harassment, stalking, and unwanted correlation of identity across platforms.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The sample profile values and dating intent text are written in Chinese, but the document does not indicate that the skill or format is region-specific or that users may choose another language. This can conflict with language/locale policy expectations when no opt-in or justification is provided.
Content: No source excerpt is available for this finding.