The Agent Skills Directory

[SAFE]: The skill consists exclusively of natural language instructions (Markdown) and does not include any executable scripts, binaries, or shell commands.
[SAFE]: No network communication, data exfiltration, or credential access patterns were detected. The skill operates entirely within the provided context of the agent.
[SAFE]: The instructions include strong safety constraints, explicitly forbidding the fabrication of identities, data, or personal experiences, and requiring strict citation of evidence via specific IDs.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data (transcribed works). While this presents a potential surface for indirect prompt injection if the source material contains malicious instructions, the skill mitigates this through requirements for structured output, mandatory citations, and the use of placeholders for missing information.

creator-agent