The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes existing context entries from the environment to inform its interview process, creating a surface for potential indirect prompt injection if those files contain malicious instructions. Ingestion points: reads context entries relevant to the plan (SKILL.md). Boundary markers: absent. Capability inventory: explores filesystem, tools, and docs, and writes decisions via /to-ctx (SKILL.md). Sanitization: absent.- [NO_CODE]: The skill is composed exclusively of Markdown instructions and YAML metadata; it does not include any scripts, binaries, or other executable files.- [SAFE]: The skill describes a standard interactive reasoning workflow and utilizes built-in agent capabilities for filesystem access and decision recording. It references a well-known public repository for attribution without downloading external code.

ctx-grill