The Agent Skills Directory

[SAFE]: The skill is purely instructional, guiding the agent on how to structure and summarize educational content. It does not include any executable code, scripts, or suspicious network requests.
[INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting external data (transcripts, slides, web links) to generate study materials. While this represents a data ingestion surface that could theoretically contain malicious instructions, the skill does not provide the agent with high-risk tools or commands that could be exploited. The lack of sensitive data access or arbitrary command execution makes this a safe, standard application of AI-assisted note-taking.

cornell-notes