The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes financial transaction data, specifically merchant descriptions and category labels, which are untrusted external inputs that could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: Untrusted data enters the agent context through the transaction_search tool described in SKILL.md.
Boundary markers: The skill body lacks specific delimiters or instructions to the agent to treat transaction content as untrusted data or to ignore embedded instructions within merchant descriptions.
Capability inventory: The skill uses transaction_search, anomaly_detect, and spending_summary to process and categorize data. It does not possess file-write or general network capabilities.
Sanitization: There is no evidence of sanitization, filtering, or validation of the text retrieved from transaction history before it is processed by the agent.

expense-optimizer