The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user-provided marketing copy and also reads context from a local file, creating a surface for indirect prompt injection attacks. * Ingestion points: The skill ingests user-supplied text for editing and reads from .claude/product-marketing-context.md (referenced in SKILL.md). * Boundary markers: The instructions do not define clear delimiters or boundary markers to separate untrusted user content from the agent's instructions. * Capability inventory: The skill involves text processing and local file reading capabilities. * Sanitization: There are no explicit instructions for sanitizing or validating the input data before processing.

copy-editing