The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Node.js script located at scripts/spec-driven.js to perform its core functions of listing, modifying, and verifying change artifacts.
[PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection as it reads and processes data from untrusted external files within the project directory.
Ingestion points: Reads content from proposal.md, design.md, tasks.md, questions.md, and various files within the specs/ directory.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when reading these files.
Capability inventory: The skill has the capability to execute shell commands via node as part of its modify and verify operations.
Sanitization: No sanitization or validation of the markdown content is performed before the agent processes the text.

spec-driven-modify