Security audit

Multi Platform Content Calendar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local content-calendar helper that writes planning and performance files in a disclosed app directory, with no evidence of hidden execution, exfiltration, or privilege abuse.

Install only if you are comfortable with a Chinese-language CLI helper creating and updating ~/content-calendar files, including local performance metrics you enter manually. Review or delete that directory if you no longer want the retained planning and engagement data.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill describes commands that read from and write to user files (for example under ~/content-calendar/) but does not declare any tool scope, permissions, or allowed-tools boundary. This creates a capability/consent mismatch: an agent may perform filesystem operations the user did not clearly authorize, increasing the risk of unintended local data creation, modification, or overwrite.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger phrases are broad, generic productivity terms such as '内容日历', '排期规划', and '内容规划', which can easily match ordinary conversation and invoke the skill unintentionally. Unexpected activation can lead to unwanted file operations, data collection, or planning actions without the user realizing a stateful skill has taken over.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill explicitly tracks engagement metrics like likes, comments, shares, favorites, and growth outcomes, but the description does not warn users that this data will be recorded and stored. This undermines informed consent and can expose sensitive business or account-performance data to unnecessary retention or accidental disclosure.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This file contains natural-language descriptions that force a specific language/locale for users, including the module docstring and subsequent CLI help/output strings. Under the policy, language constraints should either be optional or clearly justified as region-specific; this file provides no such opt-in or justification.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: The skill description and examples are entirely in Chinese and the trigger phrases are Chinese-only, with no indication that users may interact in other languages or that the Chinese-only scope is intentional. Under the stated policy, a fixed language requirement without opt-in or justification is a natural-language policy concern.

Static analysis

No suspicious patterns detected.