generate
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates within a restricted environment using local file paths (e.g.,
.taskmaster/docs/prd.md) and pre-authorized tools provided by the vendor 'anombyte93'. - [COMMAND_EXECUTION]: The skill invokes local utilities including
script.pyandtask-masterto perform template loading, validation, and task parsing. These executions are confined to the internal pipeline operations and do not involve untrusted remote sources. - [PROMPT_INJECTION]: The skill ingests data from a previous 'DISCOVER' phase to populate templates. It mitigates potential indirect prompt injection through mandatory validation steps (
mcp__plugin_prd_go__validate_prd) and a strict requirement that all placeholders must be either replaced with validated content or explicitly attributed with a reason code. - [SAFE]: A Python script is utilized via the CLI to verify the integrity and coverage of the generated
tasks.jsonfile. This code is static, visible, and serves a benign diagnostic function to ensure data consistency.
Audit Metadata