The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read external context files, creating a potential surface for indirect prompt injection.
Ingestion points: The agent is instructed to check for and read .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md to gather context about the user's product.
Boundary markers: The instructions do not include specific delimiters or warnings to treat the content of these external files as untrusted or to ignore embedded instructions.
Capability inventory: The skill is limited to generating text-based strategies, architecture plans, and calendar rituals; it does not possess system-level capabilities like file writing, shell command execution, or network access.
Sanitization: The skill does not perform any sanitization or validation of the ingested context data.

community-marketing