The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from external source files to generate a storyboard document. Ingestion points: Reads data from SCENES.md, NARRATION.md, and references/storyboard-format.md. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands in the input data. Capability inventory: The agent is limited to reading local files and writing the STORYBOARD.md file; no tools for command execution, network access, or sensitive file manipulation are utilized. Sanitization: No content validation or sanitization steps are specified.
[SAFE]: Analysis of the skill instructions and metadata found no evidence of prompt injection, data exfiltration, obfuscation, or unauthorized access attempts. The skill appears to be a standard procedural tool for video production workflows.

to-storyboard