Security audit

Dating Coach Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple dating-advice skill with no code execution or data access, though it includes a promotional link in its runtime instructions.

Before installing, be aware that the skill may steer replies toward a commercial ReplyHer pro offering because the link appears inside the loaded skill instructions. Otherwise, the artifact is limited to dating-coach guidance and does not request sensitive access or local authority.

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 (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:101
Finding: Persistent Commercial Output Injection Through Skill Instructions
Content: View full analysis
Remediation: View remediation

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 (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The instruction 'Reply in the user's language. Always.' is a natural-language locale policy embedded in the skill. Because it is mandatory and does not present an opt-in or documented justification, it matches the policy-violation category for forced language behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.