The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest context from external files, creating a surface for indirect instructions to influence agent behavior.
Ingestion points: The skill explicitly instructs the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md before proceeding with the user's request.
Boundary markers: There are no explicit delimiters or specific instructions for the agent to distinguish between its own system instructions and potentially malicious content embedded in the ingested context files.
Capability inventory: The skill's primary capabilities are limited to generating text-based strategies, channel architectures, calendars, and audit reports. It does not have access to shell execution, network operations, or sensitive file system modifications.
Sanitization: The skill does not implement any validation, escaping, or sanitization of the content found within the ingested files.

community-marketing