The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill relies on reading FOUNDER_CONTEXT.md from the project root to inform its pricing strategy. This data ingestion surface is vulnerable to indirect prompt injection if the file contains instructions intended to manipulate the agent's behavior.
Ingestion points: The agent is instructed to read FOUNDER_CONTEXT.md in the first step of Task Execution.
Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore any embedded commands within the business context file.
Capability inventory: The skill uses text generation and the AskUserQuestion tool to produce its final strategy output.
Sanitization: There is no specified validation or filtering of the external file's content before it is processed by the agent.

pricing-strategist