The Agent Skills Directory

[SAFE]: The skill is designed for static content generation and does not perform any network operations, data exfiltration, or sensitive file access. All references and execution artifacts are internal to the skill package.\n- [COMMAND_EXECUTION]: The skill includes a utility script scripts/check-output.py that validates markdown headers in a local file. This script uses standard Python libraries, does not execute arbitrary code, and poses no security risk to the agent environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided context such as business goals and personas. However, this data is used only for text generation within a fixed structure and is not processed by any dangerous tools or executable environments, resulting in a safe implementation surface.

pitch-deck-builder