The Agent Skills Directory

[NO_CODE]: The skill is composed entirely of markdown-based instructions for the AI agent. It does not include any Python or Node.js code, shell scripts, or external configuration files.
[SAFE]: A thorough review of the instructions found no evidence of prompt injection, data exfiltration attempts, or hardcoded credentials. The skill's operations are limited to text processing and document generation.
[INDIRECT_PROMPT_INJECTION]: The skill includes functionality to rewrite user-provided slide decks or old lesson plans. While this allows external data into the agent's context, the skill does not possess capabilities (such as network access or command execution) that could be exploited via indirect prompt injection. The risk is limited to the accuracy of the generated lesson plan content.
[COMMAND_EXECUTION]: The skill mentions using "document tools" to build Word documents. This refers to standard, platform-provided capabilities for file creation and does not involve arbitrary or unsafe shell command execution.

lesson-plan