The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes bundled Python scripts (ingest.py and mvsetup.py) via the Bash tool to perform video analysis. These commands use file paths derived from the local environment or user input as arguments.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests and processes untrusted video data.
Ingestion points: Video files located in the animations/ directory or specified by the user (SKILL.md).
Boundary markers: There are no explicit instructions for the agent to ignore potentially malicious content embedded within the video analysis results.
Capability inventory: The skill has access to Bash, Read, and AskUserQuestion tools.
Sanitization: The skill does not specify any sanitization or validation routines for the data extracted from video files.

analyze