The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from customer interactions, creating a surface for indirect prompt injection.
Ingestion points: External data enters the agent context through the support_data variable in the SupportAnalytics class and the customer_feedback list in the KnowledgeBaseManager class, both located in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers to isolate potentially adversarial customer input from the agent's logic.
Capability inventory: The skill includes Python execution for data analysis (calculating CSAT, response times) and reporting. It does not perform network operations or access sensitive system files.
Sanitization: There is no evidence of input validation or sanitization for the customer-supplied text before it is processed by the analytics or knowledge base logic.

support-responder