The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files (JSON format) and uses them to generate product packages. While the skill processes external data, it operates within a constrained commercial consulting context and uses standard local tools.
Ingestion points: Reads from products/, markets/, customers/, and context/ directories within the project structure (SKILL.md).
Boundary markers: None specified in the instructions.
Capability inventory: Utilizes Read, Write, Edit, Glob, Grep, and Bash tools for file manipulation and executing internal scripts.
Sanitization: No explicit data sanitization or escaping mechanisms are mentioned for the ingested data.
[COMMAND_EXECUTION]: The skill instructs the agent to execute specific shell scripts (project-status.sh, validate-entities.sh) located within the plugin's root directory. These scripts are used for status checking and schema validation. The resolution of the plugin root directory uses standard shell commands to locate the installed plugin cache.

packages