task-tracking-dots
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the
dotCLI from a GitHub repository (github.com/joelreymont/dots) or a Homebrew tap. This is the primary component for the skill's stated purpose. - [COMMAND_EXECUTION]: The skill uses shell commands to verify the installation (
command -v dot), build the tool from source (zig build), and execute task-tracking operations (dot ls,dot ready,dot on). These are standard administrative and functional commands. - [PROMPT_INJECTION]: The skill processes user-provided strings for task names and completion reasons. This presents a surface for indirect prompt injection if the inputs are derived from untrusted external sources.
- Ingestion points: Task titles and description flags in
dot addand completion reasons indot off -r. - Boundary markers: None identified in the provided command examples.
- Capability inventory: Shell execution via the
dotbinary. - Sanitization: No explicit input sanitization or validation is mentioned in the skill files.
Audit Metadata