Security audit

COMMS.md Creator

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently helps users draft a COMMS.md from user-provided communication preferences, with no hidden execution, credential use, persistence, or automatic sharing.

This skill asks personal questions about communication style, availability, boundaries, and channel preferences. Install it if you are comfortable creating that kind of document, and review the final COMMS.md carefully before saving it somewhere public or shared.

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: 91% confidence
Finding: The invocation description is broad enough that the skill may activate on generic requests about communication preferences documents, not just explicit requests for COMMS.md creation. That can cause inappropriate routing or unexpected collection/generation of personal communication-preference content in contexts where the user did not clearly ask for this specific skill.

Static analysis

No suspicious patterns detected.