The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by instructing the agent to ingest data from external files.
Ingestion points: The skill reads .agents/product-marketing-context.md or .claude/product-marketing-context.md in SKILL.md to gather business context.
Boundary markers: There are no delimiters or specific instructions to the agent to treat the contents of these files strictly as data or to ignore any embedded instructions within them.
Capability inventory: The agent processing this skill typically has access to various tools and file system operations which could be misused if malicious instructions are present in the context files.
Sanitization: The skill does not perform any validation, escaping, or filtering of the content read from the external context files.

pricing-strategy