The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user-provided requirement files (e.g., plan.md) to drive the interview and planning logic, which is a common surface for indirect prompt injection.
Ingestion points: Reads the requirement file path provided in $ARGUMENTS or defaults to plan.md in the working directory.
Boundary markers: The skill does not use specific delimiters or instructions to the agent to disregard malicious commands embedded within the input files.
Capability inventory: The skill has access to high-privilege tools including Bash (shell execution), Write (filesystem access), and Skill (executing other agent workflows).
Sanitization: There is no evidence of content sanitization or validation of the requirements file before it is integrated into the prompt context.
[COMMAND_EXECUTION]: The skill executes local shell scripts to manage the lifecycle of a Node.js web server used for its visual components.
Evidence: The skill triggers scripts/start-server.sh and scripts/stop-server.sh to run scripts/server.js via Node.js.
Scope: The server is designed to bind to 127.0.0.1 and serve files from a restricted session-specific directory, but the ability to launch network-listening processes is a significant capability.

interview-plan