st-generate-tasks
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local helper scripts (
scripts/find-strikethroo-root.cjs,scripts/validate-plan-blueprint.cjs, andscripts/get-next-task-id.cjs) to automate workspace discovery and task ID management. These are self-contained scripts included with the skill and use standard Node.js file system APIs. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface (Category 8) as it is instructed to read and follow directions from project-specific files like
POST_TASK_GENERATION_ALL.mdand plan blueprints. This assumes the project repository being processed is trustworthy. - Ingestion points: Local plan files,
<root>/config/hooks/POST_TASK_GENERATION_ALL.md, and project configuration templates. - Boundary markers: None identified; the agent is directed to follow instructions found within the hook file verbatim.
- Capability inventory: The skill can read/write local files and execute the bundled helper scripts.
- Sanitization: No explicit sanitization of the natural language content within the project files is performed before the agent processes them.
Audit Metadata