The Agent Skills Directory

[SAFE]: The skill defines routine software engineering tasks such as building prerequisites, running test suites, and debugging logs. No suspicious commands or unauthorized file access patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to inspect test traces and logs to identify root causes. While this represents a data ingestion surface where external content enters the agent's context, it is a necessary part of the functional requirement for debugging and is performed within a standard, human-in-the-loop development workflow.

run-smoke-tests