Back to skill

Security audit

Daily Review Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language daily review helper whose sensitive review export behavior is disclosed and purpose-aligned, but users should treat exported review history as private data.

Install only if you are comfortable using a Chinese-language skill that may read or export daily review files under memory/evolution/daily-review/. Review exports before sharing them because they may include conversation history, personal reflections, plans, and other sensitive notes.

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
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly supports exporting daily review content and points to a local memory path containing historical review reports, but it does not describe any access controls, consent checks, destination restrictions, or privacy warnings. Because these reviews likely contain prior conversation content, personal reflections, and potentially sensitive data, an export feature can enable unintended disclosure or bulk exfiltration if invoked casually or by an untrusted user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file’s human-readable strings and comments are entirely in Chinese, including the skill name, description scaffolding, and returned message. This indicates a language-specific constraint in natural-language content without any documented opt-in, user choice, or region-specific justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The natural-language interface examples and instructions consistently prescribe Chinese trigger phrases and usage patterns, with no indication that users may choose another language. Per policy, forcing a specific language without user opt-in can be a locale-policy issue unless the restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The package description and author metadata are written entirely in Chinese, with no indication that alternative language support is available or that the skill is region-specific. For a generally distributed skill manifest, this can constitute a natural-language policy issue because it implicitly enforces a locale without documenting user choice or justification.

Content

No source excerpt is available for this finding.