The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions include a requirement to read external context files such as .agents/product-marketing.md or .claude/product-marketing.md to tailor marketing recommendations. This ingestion of potentially untrusted data represents a surface for indirect prompt injection.
Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (identified in SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within these context files.
Capability inventory: The skill possesses no dangerous capabilities; it does not perform file writes, network operations, or shell command executions.
Sanitization: There are no sanitization or validation steps defined for the content of the ingested files.

marketing-psychology