The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by design.
Ingestion points: Processes arbitrary text provided by the user or read from files (SKILL.md).
Boundary markers: Absent. The instructions do not specify delimiters or provide guidance to the agent to ignore instructions embedded within the text being humanized.
Capability inventory: The skill is configured with Read, Write, Edit, Grep, and Glob permissions, allowing it to modify files on the system.
Sanitization: Absent. There is no logic provided to sanitize or validate the input text to prevent malicious instructions from being executed if the agent obeys them.

humanizer