Security audit

community-forum

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only community marketing guidance skill with no executable code, persistence, hidden network behavior, or privileged actions.

Before installing, be aware that this skill may activate for broad community or marketing requests. It is otherwise low-risk: it gives strategic guidance and may read local project context files only to tailor product, audience, and brand voice recommendations.

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
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger description is very broad and includes many generic marketing terms, so the skill may activate for loosely related requests and steer the agent into community-promotion guidance when another skill would be more appropriate. This can cause misrouting, lower-quality outputs, and accidental disclosure or use of project context for the wrong task if the skill is invoked too eagerly.

Static analysis

No suspicious patterns detected.