skills/openclaw/skills/todoist/Gen Agent Trust Hub

todoist

Fail

Audited by Gen Agent Trust Hub on Feb 14, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [CREDENTIALS_UNSAFE] (HIGH): The skill identifies and relies upon the configuration file path ~/.config/todoist/config.json. This file stores a sensitive Todoist API token in plaintext, posing a risk of credential exposure if accessed by the agent or other processes.- [PROMPT_INJECTION] (HIGH): The skill is vulnerable to indirect prompt injection because it processes external task data and has destructive write capabilities. * Ingestion points: External task descriptions and metadata retrieved via todoist list. * Boundary markers: None. The skill does not instruct the agent to use delimiters or ignore instructions embedded within task content. * Capability inventory: todoist add, todoist modify, todoist close, and todoist delete provide side-effect capabilities. * Sanitization: None detected. External content is processed as raw strings.
  • [EXTERNAL_DOWNLOADS] (MEDIUM): The skill requires the installation of todoist-cli via Homebrew from an untrusted GitHub repository (sachaos/todoist).
  • [COMMAND_EXECUTION] (LOW): The skill operates by executing shell commands through the todoist binary. While routine for CLI-based skills, this increases the potential impact of any injected arguments.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 14, 2026, 06:02 PM