Security audit

Voice Match Humanizer

Security checks for vulnerabilities and agentic risk

Overview

This local, instruction-only writing-voice skill is mostly coherent, but it needs review because user-supplied profile names are used for local file reads, writes, and deletes without explicit path-safety rules.

Before installing, be comfortable with the assistant reading writing samples you point it to and storing reusable voice profiles locally. Use simple profile and platform names only, and confirm any create, update, or delete operation targets a file under the local profiles/ directory. Avoid sensitive samples unless you trust the runtime's file-access controls.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:124
Finding: Path Traversal Through Unvalidated Profile and Platform Names
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep