The Agent Skills Directory

[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting external data from local context files.
Ingestion points: The skill reads content from files such as .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md if they exist in the environment.
Boundary markers: The instructions lack explicit boundary markers or directives to the agent to treat the content of these files strictly as data rather than instructions.
Capability inventory: The skill uses this information to perform content planning and strategy recommendations. It does not have access to sensitive tools, code execution, or non-whitelisted network resources.
Sanitization: There is no evidence of filtering or sanitization applied to the content ingested from these external files.

lead-magnets