The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting data from external context files into the agent's reasoning process without established safety boundaries.
Ingestion points: The files .agents/product-marketing-context.md and .claude/product-marketing-context.md are read and processed by the agent.
Boundary markers: Absent. The instructions do not specify any delimiters or warnings to the agent to treat the contents of these context files as potentially untrusted data.
Capability inventory: The skill provides informational advice and role-play as a marketing expert; it does not explicitly invoke high-risk tools like shell execution, network requests, or file-writing capabilities in the provided code.
Sanitization: Absent. There are no instructions to validate, filter, or escape content read from the external files before it is processed by the model.

marketing-psychology