The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted data from the repository, including source code, game design documents, and narrative files, which may contain malicious instructions.\n
Ingestion points: Files are read from Assets/Game/, design/gdd/, and design/narrative/ as described in references/claude-skill.md.\n
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted data from the agent's core logic.\n
Capability inventory: The skill has access to high-privilege tools including Bash, Write, and Task (used to spawn sub-agents) as listed in the allowed-tools frontmatter of references/claude-skill.md.\n
Sanitization: The workflow lacks explicit steps for sanitizing, escaping, or validating the content of external documents before they are incorporated into the agent's context.

localize