The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is configured to automatically ingest data from external context files, which serves as a potential attack surface for indirect prompt injection.
Ingestion points: The instructions direct the agent to read context from files such as .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the data in these files and its primary behavioral instructions.
Capability inventory: The skill allows the agent to generate marketing copy, define SEO architecture, and output structured YAML data for competitor profiles.
Sanitization: No sanitization, validation, or filtering mechanisms are defined for the content retrieved from the specified context files.

competitors