The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its data processing requirements.
Ingestion points: The skill instructs the agent to read context from user-controlled files such as .agents/product-marketing.md or .claude/product-marketing.md and to process user-provided marketing copy.
Boundary markers: No specific delimiters or 'ignore instructions' warnings are provided to prevent the agent from accidentally obeying commands embedded within the marketing content or context files.
Capability inventory: The skill does not provide any capabilities for network access, file system writes, or shell command execution, limiting the potential impact of an injection.
Sanitization: No input validation or sanitization is performed on the ingested content.

copy-editing