The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input supplied via the $ARGUMENTS parameter.
Ingestion points: User input is ingested through the $ARGUMENTS variable in SKILL.md for text transformation.
Boundary markers: The skill does not implement delimiters to isolate user-provided data from the underlying instructions.
Capability inventory: No capabilities for command execution, network operations, or file system modifications are present within the skill configuration.
Sanitization: The skill does not perform sanitization or filtering on the input text before processing.

ste