Back to skill

Security audit

Memory Four Types

Security checks for vulnerabilities and agentic risk

Overview

This memory-management skill is not malware, but it encourages broad long-term storage of personal details and conversation logs without clear consent or deletion controls.

Install only if you are comfortable with the agent creating persistent workspace memory files. Before using it, require explicit consent before saving user details, avoid raw conversation logs, remove contact information unless essential, redact private data beyond API keys, and define review, deletion, and retention rules for the memory directory.

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)

other

Warning
Location
SKILL.md:27
Finding

Excessive Persistent Collection of Personal and Conversational Data

Content
View full analysis
Remediation
View remediation
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 (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description declares trigger words including “记忆管理” and “记忆分类” without constraining context, scope, or exclusion cases. These phrases are generic enough that ordinary discussion about memory organization could unintentionally invoke the skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly encourages storing user identity, preferences, and background information, but it does not require user consent, notice, minimization, or a retention policy tied to privacy expectations. This creates a real privacy and data-protection risk because an agent may persist personal data users did not expect to be stored long-term, increasing exposure in later sessions or shared workspaces.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction to write interesting daily conversations into raw logs encourages retention of free-form natural-language content that can easily include secrets, personal data, internal URLs, credentials, or sensitive business context. Even with some token-pattern scanning elsewhere, raw conversational logs are hard to sanitize reliably, so this materially increases the risk of data leakage, over-retention, and later unintended disclosure.

Content

No source excerpt is available for this finding.

Ssd 3

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Describing daily logs as a place where 'everything' is recorded normalizes indiscriminate data collection and conflicts with the earlier principle of selective memory storage. In practice, this leads to over-collection of user-provided data, including sensitive or regulated information, and broadens the blast radius if the memory directory is later accessed by other sessions, agents, or users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown template is written entirely in Chinese, including field values and section labels, with no indication that users may choose another language. That creates a natural-language policy concern because it imposes a specific language by default without opt-in or a stated region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This template is entirely written in Chinese, including the name, description, heading, and field labels, with no indication that the user can choose another language. That can violate a language/locale policy when a skill or template forces a specific language without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown template is primarily written in Chinese, but L17 introduces an English section header. The file does not indicate that language choice is optional or user-selectable, so it may violate language/locale consistency policy by implicitly forcing mixed-language output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The template’s visible field values and section content are entirely in Chinese, which implies a fixed output language for users of this skill artifact. There is no accompanying note that the language is optional, user-selectable, or required for a specific regional/compliance context.

Content

No source excerpt is available for this finding.