The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted text from users or external files through the Read tool. It has the capability to modify content using Write and Edit tools.
Ingestion points: Text provided by the user in dialogue or read from local files via the Read tool as specified in SKILL.md and README.md.
Boundary markers: Absent. The instructions do not mandate the use of delimiters or XML tags to separate user content from system instructions.
Capability inventory: The skill is authorized to use Read, Write, Edit, and AskUserQuestion tools, allowing it to modify the file system based on its analysis of input text.
Sanitization: None observed. The agent is instructed to process the text directly to identify and rewrite AI patterns without a sanitization layer for embedded instructions.

humanizer-zh