The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from local context files which could potentially contain malicious instructions.
Ingestion points: The skill instructions in SKILL.md direct the agent to read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md if they exist.
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within these external files.
Capability inventory: The skill possesses no high-risk capabilities; it does not perform network operations, file writes, or subprocess/code execution. It is purely advisory.
Sanitization: No sanitization or validation of the input file content is mentioned.

marketing-psychology