The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as meeting transcripts, recordings, and raw notes.
Ingestion points: The 'Operational Workflow' and 'Example Prompts' sections in SKILL.md explicitly instruct the agent to process external inputs.
Boundary markers: The example prompts provided do not use specific delimiters (e.g., triple backticks) to wrap the pasted transcript content, which is a standard surface for indirect instructions.
Capability inventory: The skill does not utilize any high-risk tools, shell commands, or network-enabled tools. Its actions are limited to generating structured text output.
Sanitization: No specific sanitization or filtering logic is defined for the input text.
[SAFE]: The skill does not contain any executable scripts, binary files, or automated system commands. It functions strictly as a set of logical instructions for the AI agent.

meeting-minutes