Security audit

Weekly Content Planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local content-calendar template generator with minor disclosure and accuracy issues, not evidence of malicious behavior.

Before installing, understand that this is a local template generator, not a full AI copywriter. It creates or overwrites content-calendar.md in the current directory, so run it from a folder where that filename is safe to replace.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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 (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared description promises generation of a full week of social media content with platform-optimized posts. However, the script only scaffolds a markdown content calendar with bracketed placeholders such as '[Your tweet here]' and '[Compelling headline...]' rather than producing actual completed posts. It does include hashtags and posting times and targets the stated platforms, so the overall domain is aligned, but the core capability is overstated: it outputs a template for drafts, not full generated content.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The trigger phrase is broad enough that the skill could activate on generic marketing or content-planning requests beyond the user's specific intent. In an agent environment, overly broad triggers can cause incorrect tool invocation, unexpected file creation, or routing user data into a skill they did not mean to use.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The description defines a wide activation scope without constraints, increasing the chance that an orchestrator selects this skill for loosely related requests. While the content domain is low risk, ambiguous routing can still lead to unintended behavior, misleading output, or side effects like creating files in the working directory.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill notes in output details that it creates content-calendar.md, but it does not prominently warn users in the high-level description or invocation contract that it writes to the current directory. Undisclosed filesystem side effects reduce user consent and can surprise an agent workflow that assumes read-only or message-only behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.