The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided text for rewriting and humanization. This presents an attack surface where instructions embedded in the source text could attempt to influence agent behavior.
Ingestion points: User-supplied text to be edited, rewritten, or reviewed as described in the SKILL.md frontmatter.
Boundary markers: None identified. The instructions do not specify using delimiters or explicit warnings for the agent to ignore instructions found within the input text.
Capability inventory: None. The skill contains only text-based instructions and does not utilize any shell tools, network capabilities, or file system write access.
Sanitization: None identified.
[NO_CODE]: The skill consists entirely of instructional markdown content. No executable scripts, binaries, or configuration files for remote execution are present.

humanizer