Security audit

daily-viz

Security checks for vulnerabilities and agentic risk

Overview

This is a small local daily-tracking skill that stores user-entered records locally and prints simple charts, with some documentation overclaiming but no hidden or unsafe behavior found.

Install only if you are comfortable storing mood, sleep, exercise, work, and notes as local JSON under ~/.daily-viz/data/. Treat advertised features like AI advice, PDF export, cloud sync, and encryption as not evidenced in this package unless separately implemented or documented.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (9)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 90% confidence
Finding: The declared description presents a broader daily life tracking tool that records multiple categories of data and generates charts and insights. The supplied code chunk only performs local file reading and simple console-based visualization for existing records, specifically mood counts and recent exercise minutes. It does not record data, and it does not handle sleep or work-hours visualization in this snippet. While the visualization aspect is consistent with the description, the actual behavior is significantly narrower than the declared purpose, so this is a description/behavior mismatch.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file switches into Chinese for the title, feature descriptions, and all example commands, which effectively forces a specific language for use of the skill. There is no opt-in, alternative language option, or justification that the skill is intended only for a Chinese-speaking or region-specific audience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The manifest description is written entirely in Chinese and presents the skill in a single language, which can indicate a locale or language constraint without offering the user an explicit choice. Under the policy, language-specific behavior should be opt-in or clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file description and all user-facing console messages are in Chinese, indicating the skill is designed to operate in a single language. There is no opt-in, fallback, or documented justification that this is a region-specific tool, so this is a natural-language locale policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The skill title and usage examples are entirely in Chinese, and the invocation examples imply the skill is expected to be used in that language. Because no language choice or opt-in is offered, this can be considered a natural-language policy issue under the language/locale rule.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The README describes recording, analyzing, and exporting sensitive daily-life information such as mood, sleep, exercise, and work patterns, but provides no privacy warning or guidance about handling that data. This can lead users to unknowingly store or export personal behavioral data without understanding retention, sharing, or exposure risks.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The author metadata uses a non-English name string, which can indicate a language-specific presentation context in skill metadata without any documented language or locale choice. For a general-purpose skill package, there is no accompanying justification that this skill is region-specific or offers locale flexibility.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file includes a Chinese-only module description and later emits Chinese-only usage and success messages, which imposes a specific language on all users. The policy allows locale constraints only when users are given a choice or the restriction is clearly documented and justified, neither of which appears here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.