The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to read from local files to obtain product marketing context, which presents a surface for potential indirect prompt injection.
Ingestion points: The skill attempts to read context from .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested data are defined.
Capability inventory: The skill instructions do not invoke any high-risk capabilities such as shell command execution, sensitive file modification, or network operations.
Sanitization: There are no explicit instructions for sanitizing or validating the data retrieved from the context files before it is processed by the agent.

onboarding