task-tracking-dots

Warn

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the 'dot' CLI tool from a third-party Homebrew tap ('joelreymont/tap/dots') or by cloning a GitHub repository ('github.com/joelreymont/dots.git'). These sources are external to the vendor and not on the trusted organizations list.\n- [COMMAND_EXECUTION]: The skill involves executing several shell commands for installation and operation:\n
  • 'brew install joelreymont/tap/dots' for package installation.\n
  • 'git clone', 'zig build', and 'cp' for manual installation from source.\n
  • Regular use of the 'dot' CLI (e.g., 'dot ls', 'dot on', 'dot off') to perform task management operations.\n- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by ingesting data from the 'dot' tool's output into the agent's context.\n
  • Ingestion points: Task data is read via 'dot ls', 'dot ready', 'dot show', 'dot tree', and 'dot find' (SKILL.md, commands/task-tracking-dots.md).\n
  • Boundary markers: The skill lacks explicit boundary markers or instructions to the agent to disregard potential instructions embedded within the task data.\n
  • Capability inventory: The agent has the capability to execute shell commands using the 'dot' CLI tool.\n
  • Sanitization: There is no evidence of sanitization or verification of the data returned by the 'dot' tool before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 13, 2026, 02:43 PM
Security Audit — agent-trust-hub — task-tracking-dots