Back to skill

Security audit

Todo4google

Security checks for vulnerabilities and agentic risk

Overview

The skill has a coherent todo-to-Google workflow, but its documented shell commands use unsafe interpolation for task data and file paths, creating a real review-worthy command-injection risk.

Review this skill before installing. Its core behavior is understandable, but only use it with trusted todo content and file paths, and prefer an implementation that calls gog with structured arguments rather than assembled shell strings. Be aware that syncing or archiving sends selected todo/work-log data to Google services.

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

Error
Location
SKILL.md:112
Finding

Shell Command Injection Through Unsafe Placeholder Interpolation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly syncs local todo content and work logs to Google Tasks and uploads files to Google Drive, but it does not warn the user that task titles, notes, dates, and archived files will be transmitted to external cloud services. This creates a real privacy and data-handling risk because users may unknowingly expose sensitive work information outside the local environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The archive function uploads a local todo file to Google Drive and converts it to a Google Doc, but it lacks an explicit privacy or data-transfer warning. Because todo files may contain work logs, summaries, deadlines, and notes, this can expose sensitive operational or personal information to a third-party cloud platform if the user does not fully understand the transfer.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill automatically creates and modifies local markdown todo files as part of normal operation, but it does not clearly warn the user about filesystem changes. While this is expected for a todo manager, silent file creation and editing can still surprise users, overwrite expected content structure, or persist sensitive information locally without informed consent.

Content

No source excerpt is available for this finding.