The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security risks were identified. The skill is entirely instructional markdown meant to guide the agent's planning process.\n- [COMMAND_EXECUTION] (SAFE): Examples of terminal commands (like npx create-next-app and curl) are provided in the documentation as reference for what the AI should include in its generated plan files; they are not executed by the skill itself.\n- [DATA_EXPOSURE] (SAFE): The skill uses read-only tools (Read, Glob, Grep) for project navigation and planning context. No instructions were found that attempt to exfiltrate data or access sensitive credential files.\n- [PROMPT_INJECTION] (SAFE): The skill defines how to generate plans based on project files and user input, which constitutes an Indirect Prompt Injection surface. However, the risk is minimal given the restricted toolset and the textual nature of the output.\n
Ingestion points: Project source code and documentation files via Read, Glob, and Grep.\n
Boundary markers: No explicit delimiters or isolation instructions are provided for the plan generation.\n
Capability inventory: Limited to Read, Glob, and Grep.\n
Sanitization: No sanitization or validation of the ingested project data is performed.

plan-writing