The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to orchestrate parallel tasks and execute local helper scripts (e.g., .claude/lib/action-report-lib.sh) for tracking progress and generating reports. This behavior is consistent with the skill's stated purpose as a developer productivity tool.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it takes user-provided task descriptions and interpolates them into the prompts for sub-agents without explicit sanitization.
Ingestion points: User input provided via the /parallel command or task-specific prompts in SKILL.md examples.
Boundary markers: None are defined to separate user input from agent instructions.
Capability inventory: The skill has access to Bash execution, file modifications via Write/Edit, and the ability to spawn further sub-agents via the Task tool.
Sanitization: No sanitization or escaping of the user-provided task strings is performed before they are passed to the sub-agent context.

parallel