Security audit

diary

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it deserves review because it can automatically turn prior interactions into saved diary entries and send them to configured channels.

Install only if you are comfortable with an automated diary that may summarize interactions, save them locally, and send them to a configured destination. Use a private target, disable interaction inclusion if unnecessary, and require preview or confirmation before any send action.

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

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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger description is overly broad because it activates on common terms like “日记”, “心情”, and “每日记录”, which are likely to appear in normal conversation outside the user’s intent to invoke this skill. In this skill’s context, accidental invocation is more dangerous because the skill is designed to store reflective content and send it through a configured channel, increasing the chance of unintended data handling or disclosure.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description explains automated diary writing and sending, but it does not clearly warn that diary entries may be derived from prior user interactions and then persisted to disk and transmitted externally. This is dangerous because users may not realize their conversations can be transformed into stored summaries and pushed to channels like group chats or messaging targets, creating privacy and confidentiality risks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The template headings and prompts are written entirely in Chinese, which directs the skill to generate diary content in a specific language. There is no indication that the user can choose another language or that this locale restriction is justified by a documented region-specific purpose.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The persona is configured with the fixed name "AI助手", and the setup note is also written in Chinese, which suggests a default language/locale assumption without any visible opt-in or alternative. Under the policy rule, fixed language behavior can be a natural-language policy concern when no user choice or justification is documented.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.