Back to skill

Security audit

Empathic Trinity Core

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent memory-migration tool, but it directs agents to read and rewrite persistent memory and agent-instruction files without clear consent, review, or backup steps.

Install only if you want this skill to reorganize your workspace memory system. Before using it, review the planned changes to AGENTS.md, MEMORY.md, SOUL.md, USER.md, and memory daily files, make a backup or commit first, and avoid granting broad tool permissions unless the specific file changes are clear.

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
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description is written in Chinese and does not indicate that other languages are supported or that the language requirement is optional. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs the agent to read and restructure memory-related files such as AGENTS.md, SOUL.md, USER.md, MEMORY.md, and daily logs, which are likely to contain sensitive personal preferences, relationship notes, and historical context. In a skill whose purpose is memory migration this access is functionally relevant, but the lack of any privacy warning, consent checkpoint, or data-minimization guidance makes it a real privacy and data-handling weakness rather than a false positive.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill directs the agent to rewrite AGENTS.md and MEMORY.md and later create or normalize daily memory files and templates, causing persistent workspace changes. Although these modifications are central to the installation workflow, the skill does not require a clear warning, backup, dry-run, diff review, or user approval before destructive edits, creating risk of unintended data loss, policy changes, or privacy-impacting persistence.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file is written entirely in Chinese, beginning at the section headings and continuing through all operational guidance. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in, and this document does not offer an alternative language or explain that the Chinese-only format is required for a justified region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This file is a markdown document, so natural-language policy checks apply. The phrase "small first,need-based expansion" is presented as the core principle without offering a language choice or explaining why English is required, which may conflict with a language/locale policy that avoids forcing a specific language absent user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.