Back to skill

Security audit

Deepsync

Security checks for vulnerabilities and agentic risk

Overview

This placeholder skill has no executable code, but it asks users into sensitive psychological profiling with broad triggers and an unsupported always-local privacy claim.

Review this carefully before installing if you may ask ordinary matchmaking questions. It is not technically dangerous as packaged, but it can steer conversations toward sensitive self-disclosure, and the privacy claim should be treated as unproven until the publisher documents how data is collected, processed, stored, and kept local.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad enough to match ordinary requests such as 'find me a partner' or 'who am I compatible with,' which can cause the skill to activate unexpectedly. Because this skill deals with intimate psychological profiling, accidental invocation increases the risk of collecting or inferring sensitive personal data in contexts where the user did not explicitly intend to use DeepSync.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation makes a strong privacy/security assurance ('Your data stays local. Always.') while the skill is only a placeholder and provides no implementation demonstrating that guarantee. In a skill centered on deep psychological profiling and partner matching, misleading users about data locality can cause them to disclose highly sensitive personal information under false assumptions.

Content

No source excerpt is available for this finding.