The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and processes externally-provided specification files (Markdown and Gherkin) to generate tasks and guide subagent reviews.
Ingestion points: Reads proposal.md, features/*.feature, design.md, and beat/config.yaml in Step 3.
Boundary markers: No specific delimiters or safety instructions are used to isolate the content of these artifacts when they are interpolated into prompts for task generation tools or subagents.
Capability inventory: The skill can write to tasks.md, execute git commands, and spawn review subagents.
Sanitization: No content validation or sanitization is performed on the input specification artifacts.
[COMMAND_EXECUTION]: The skill uses standard version control commands, specifically git add and git commit, to persist the generated task list and status updates.

plan