The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and process external data sources such as OpenAPI specifications, Protobuf contracts, and issue descriptions to generate test cases.
Ingestion points: Processes external specifications and feature tickets as described in the scoping and authoring steps of the process.
Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when reading content from these external files.
Capability inventory: The skill utilizes powerful tools including execute_command, write_file, and run_tests which could be targeted by malicious payloads embedded in specifications.
Sanitization: No explicit sanitization or content validation steps are defined for external data before it influences code generation or command execution.

write-tests