Security audit

Cn Holiday Reminder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent holiday and relationship reminder, but it stores intimate relationship details locally and may send reminder content to Feishu without strong privacy controls.

Install only if you are comfortable storing relationship dates and names in a plaintext local file and, if reminders are enabled, potentially sending reminder text through Feishu. Prefer using a private machine/account, review or restrict ~/agent-memory/love.json permissions, and avoid enabling Feishu delivery for sensitive reminders unless the destination is private.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/love.py:49
Finding: Relationship Data Stored and Exposed Without Adequate Privacy Controls
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (10)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: This second mismatch finding highlights the inverse problem: the document advertises harmless query features while also introducing storage of sensitive relationship information in ~/agent-memory/love.json without clearly declaring that behavior in a permission model. Such discrepancies reduce transparency and can lead to collection or retention of personal data outside user expectations.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: This second mismatch finding highlights the inverse problem: the document advertises harmless query features while also introducing storage of sensitive relationship information in ~/agent-memory/love.json without clearly declaring that behavior in a permission model. Such discrepancies reduce transparency and can lead to collection or retention of personal data outside user expectations.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill asks the agent to collect and store sensitive relationship data including partner name, anniversary, birthday, and custom milestones, but provides no privacy warning, retention notice, or consent mechanism. Because these are intimate personal details, silent collection and local persistence materially increase privacy risk if the data is mishandled, exposed, or accessed by other components.
Content: No source excerpt is available for this finding.

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The cron reminder section configures delivery via Feishu and may send intimate reminders such as anniversaries and birthdays, yet it does not warn the user that personal relationship information could be transmitted to an external messaging channel. This creates a real confidentiality risk, especially if the Feishu destination is shared, misconfigured, or monitored by others.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill instructs the agent to directly read and write local files such as ~/agent-memory/love.json, but it does not declare any explicit tool scope or permissions. This creates a hidden capability gap where the runtime may permit file access without the user or platform clearly understanding that sensitive personal data will be persisted locally.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger wording is very broad, allowing activation on essentially any holiday- or relationship-related question. Overbroad routing increases the chance the skill is invoked in contexts where users did not intend relationship data collection, file persistence, or reminder setup, which can expand exposure of sensitive personal information.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The manifest describes both Chinese holiday functions and a romance assistant module with anniversary countdowns, birthday reminders, custom anniversaries, and romantic festival reminders. This script contains only static holiday calendar data and CLI operations for holiday/workday lookup, next holiday, calendar display, and alerts; there is no code for relationship anniversaries, birthdays, or custom reminder management.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This code hardcodes Chinese-language strings throughout its CLI output and labels the tool specifically as a Chinese holiday helper, with no option for users to select another language or locale. The policy for all file types calls for flagging language/locale constraints when they force a specific language without user opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill's user-facing strings, holiday names, prompts, help text, and tips are predominantly in Chinese, and there is no opt-in or alternative language path. This creates a natural-language policy concern because the skill effectively imposes a specific language/locale on users without explicit choice or justification.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The script stores highly sensitive personal relationship data, including partner name, anniversaries, birthdays, and custom dates, in a predictable plaintext JSON file under the user's home directory without any privacy notice, permission hardening, or encryption. In the context of an agent skill, this increases the risk of unintended disclosure to other local users, backup systems, logs, or other components that can access the same filesystem.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.