The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted text from users or files to perform its humanization task.
Ingestion points: Input text provided via $ARGUMENTS and file content accessed through the --file flag in SKILL.md.
Boundary markers: The instructions lack delimiters (e.g., XML tags or triple quotes) or "ignore embedded instructions" warnings for the text being processed.
Capability inventory: The skill utilizes Read, Write, Edit, Grep, and Glob tools, which could be misused if the agent obeys instructions embedded within the text it is tasked to humanize.
Sanitization: No sanitization or validation of the input text is performed before it is added to the agent's context.

humanizer