The Agent Skills Directory

NO_CODE (SAFE): The skill does not include any executable scripts, binaries, or package dependencies. It is composed of static Markdown files.\n- DATA_EXPOSURE (SAFE): No hardcoded credentials or access to sensitive system paths were detected. The skill only interacts with its own theme configuration files.\n- INDIRECT PROMPT INJECTION (SAFE): The skill ingests user input for theme selection and creation. While this is an ingestion surface (Category 8), the lack of executable code in the skill prevents exploitation, and the instructions mandate a human review step before applying any generated content. 1. Ingestion points: User input for theme choice and custom theme descriptions in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: No scripts; agent-level tools only. 4. Sanitization: Instructions require the agent to show generated themes for user review and verification.

theme-factory