The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes content from an external file (app-marketing-context.md), which acts as an ingestion point for data that could potentially contain malicious instructions.
Ingestion points: The app-marketing-context.md file referenced in the 'Initial Assessment' workflow.
Boundary markers: Absent; the skill instructions do not specify any delimiters or directives to the agent to distinguish between data and embedded instructions.
Capability inventory: The skill is designed to coordinate with other functional tools like keyword-research and metadata-optimization to perform its tasks.
Sanitization: Absent; there is no logic provided to validate or sanitize the information retrieved from the context file.

localization