The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided source material as its primary function. While this creates a vulnerability surface where instructions hidden in input data could attempt to influence the agent, the skill implements a multi-stage workflow (content analysis, planning, and blueprinting) combined with explicit manual verification gates for all generated text and numbers, which effectively mitigates the risk.
[EXTERNAL_DOWNLOADS]: The documentation references an external GitHub repository as the source of its methodology. However, no runtime network requests or remote code executions are initiated; all functional references are directed to local files within the skill package.
[COMMAND_EXECUTION]: The skill utilizes the host-provided imagegen tool to render final presentation slides. This is a legitimate functional requirement and does not involve arbitrary shell command execution or unauthorized system access.
[NO_CODE]: The skill consists entirely of instructional Markdown and YAML configuration files. It does not include any executable scripts, binaries, or automated installation procedures, significantly reducing the potential for traditional malware behaviors.

ppt-forge