The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes a file (skill-report.json) that contains a pre-fabricated security audit report. This report explicitly claims the skill is safe and dismisses potential automated findings as false positives. This self-referential content is an attempt to influence the agent's or analyzer's security evaluation through deceptive instructions.
[SAFE]: The core functionality of the skill is provided through Markdown instructions and prompt templates. These materials guide the agent on how to use a presentation tool (html2pptx) to create slides. The skill does not contain any executable code, shell scripts, or commands that interact with the filesystem or network.
[SAFE]: No hardcoded credentials, sensitive file paths, or unauthorized data exfiltration patterns were found within the skill's reference files or templates.

pptx-generation