The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes external source code which could contain hidden instructions intended to influence the agent. * Ingestion points: Files within the directory specified by scanPath (SKILL.md). * Boundary markers: The instructions do not define specific delimiters to separate code content from instructions. * Capability inventory: The skill is permitted to use Read, Write, Edit, Bash, Glob, and Grep tools (SKILL.md). * Sanitization: There is no mention of content sanitization or validation before the source code is processed for component inventory.

component-inventory