The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from repository files which creates a surface for indirect prompt injection. Ingestion points: Reads content from CLAUDE.md and AGENTS.md as described in SKILL.md. Boundary markers: None explicitly defined to isolate external file content within the prompt. Capability inventory: The skill performs file read and write operations on documentation files within the repository. Sanitization: No validation or filtering of content from the files is mentioned in the workflow.

agents-md