The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external text provided through the $ARGUMENTS variable to perform auditing and rewriting tasks.
Ingestion points: The $ARGUMENTS placeholder in SKILL.md is the primary entry point for untrusted user data.
Boundary markers: The skill instructions do not specify the use of delimiters or clear boundary markers to distinguish user-provided content from the skill's own instructions.
Capability inventory: No dangerous capabilities were detected; the skill does not use tools for network operations, file writing, or subprocess execution in SKILL.md, references/contexts.md, or references/rules.md.
Sanitization: There are no instructions for sanitizing or filtering the input text before processing.

simple-english