Back to skill

Security audit

Eternal Task Board

Security checks for vulnerabilities and agentic risk

Overview

This is a local task-board CLI that writes a small JSON task database; it has minor deletion and scoping caveats but no hidden network, credential, or persistence behavior.

Before installing, understand that this skill stores tasks in a local JSON file, defaults to .tasks.json, and can write to another path if --db is used. Treat remove as permanent unless you have a backup of that database file.

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
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill documents file-writing capability via a CLI task database but does not declare any tool scope, permissions, or allowed-tools boundaries. That omission weakens reviewability and enforcement, because consumers cannot tell what filesystem access is expected or constrain the skill to only the minimal write targets it needs.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The markdown describes a remove command that deletes a task, which affects user data. The file does not mention whether removal is irreversible, whether confirmation is required, or where the deleted data goes, so users are not warned about the destructive behavior.

Content

No source excerpt is available for this finding.