The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external transaction data which is an untrusted input source.
Ingestion points: The skill ingests data from the transaction_search tool as described in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within transaction descriptions.
Capability inventory: The skill is restricted to data processing and summary presentation; it does not have tools for network access, file writing, or command execution.
Sanitization: No sanitization of the transaction descriptions is performed before the agent processes them.

insurance-audit