Security audit

F5tts Monitor

Security checks for vulnerabilities and agentic risk

Overview

This is a small monitoring-only skill whose only notable risk is a disclosed local status-file update.

Before installing, confirm that you want this skill to use SSH to the Local-LLM host and that HEARTBEAT.md updates should only be made in a known local project path. There is no evidence of hidden execution, exfiltration, destructive behavior, or bundled code.

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

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

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill explicitly instructs the agent to update local HEARTBEAT.md files after monitoring, which is a state-changing file write unrelated to merely observing remote training status. Because the write is not paired with an explicit user confirmation or warning, the skill can cause unintended local modifications and create a channel for silent persistence or misleading status reporting.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.