The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external context file, which creates a potential vulnerability surface for indirect instructions to influence agent behavior.
Ingestion points: The skill instructions in SKILL.md explicitly direct the agent to read .agents/marketing-context.md if it exists.
Boundary markers: There are no explicit delimiters or boundary markers defined in the instructions to separate the context data from the agent's primary instructions.
Capability inventory: The skill is primarily focused on analysis, planning, and text generation. It does not utilize tools for network operations, file writing, or system command execution.
Sanitization: The skill lacks mechanisms for sanitizing or validating the content of the ingested markdown file.

offers