The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the lfy-cli utility by interpolating user-supplied strings like <keywords> and <gtm_id> directly into a shell command's JSON argument. This creates a risk of command injection if the agent fails to properly sanitize inputs that could break out of the single-quoted string context or the JSON structure.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing data retrieved from external CLI tool outputs without proper sanitization.
Ingestion points: Data is ingested from the stdout of lfy-cli pipeline search and lfy-cli pipeline get_sales_stage (as documented in references/search.md and references/get_sales_stage.md).
Boundary markers: The skill does not define clear delimiters or provide instructions to the agent to treat the external tool output as untrusted or separate from the primary instructions.
Capability inventory: The skill possesses the capability to execute shell commands via the lfy-cli binary.
Sanitization: There is no evidence of data validation, escaping, or sanitization of the content returned by the external business systems before it is presented to or processed by the agent.

lfy-pipeline