The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided text, articles, and writing samples for the purpose of 'humanizing' the content. This ingestion of untrusted data represents an attack surface for indirect prompt injection where malicious instructions could be embedded in the source text.
Ingestion points: User-provided drafts, articles, and writing samples passed to the agent for processing as described in SKILL.md and references/voice-calibration.md.
Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or provide guidance to ignore instructions within the processed text.
Capability inventory: The skill utilizes the Read, Write, Edit, Grep, and Glob tools to perform its tasks.
Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the text being humanized before processing it.

humanizer