The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest data from an external file, which could contain instructions that influence the agent's behavior.
Ingestion points: The file .claude/product-marketing-context.md is read by the agent if it exists.
Boundary markers: The instructions do not specify any delimiters or safety prompts to isolate content from the context file.
Capability inventory: The skill has no dangerous capabilities such as file system writes, network requests, or shell command execution, limiting the impact of any potential injection.
Sanitization: There are no instructions for sanitizing or validating the contents of the context file.

launch-strategy