The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and processes external data from files like .business/context.md and customer evidence. While these are the intended inputs for pricing analysis, maliciously formatted data within these files could theoretically influence the agent's reasoning.
Ingestion points: Processes files in the .business/ directory including context, metrics, and sales data.
Boundary markers: The skill does not currently use explicit delimiters or instructions to ignore embedded commands within the ingested data.
Capability inventory: The skill is restricted to reading local files and writing recommendations back to the .business/ directory.
Sanitization: No automated sanitization of the input file content is specified.

set-pricing