The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external context files, which could contain malicious instructions if the environment is compromised.
Ingestion points: The skill instructs the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding with tasks (found in SKILL.md).
Boundary markers: There are no instructions to use delimiters or ignore instructions found within these external context files.
Capability inventory: The skill provides instructions for generating and implementing JSON-LD markup, which involves modifying website source code or templates.
Sanitization: There is no mention of sanitizing or validating the content retrieved from the marketing context files.

schema