Security audit

humantoday

Security checks for vulnerabilities and agentic risk

Overview

This is a plain writing-editing skill with no hidden execution, persistence, credential use, or data movement.

This skill is reasonable to install if you want an opinionated editor for making drafts sound less generic. Be aware it may trigger on broad writing-improvement requests, so users who prefer a different style should invoke another writing workflow explicitly.

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: 94% confidence
Finding: The skill description is broad enough to match many generic writing-assistance requests, including requests to make text 'clearer,' 'more direct,' or 'more opinionated.' In an agent ecosystem, ambiguous trigger boundaries can cause the skill to activate unexpectedly, override a more appropriate specialist skill, or process user content it was not clearly intended to handle, which increases the risk of misrouting and policy bypass through overbroad delegation.

Static analysis

No suspicious patterns detected.