The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local Python audit scripts (trace_lint.py and trace_build_rtm.py) located in the plugins/testany-eng/ directory. These are vendor-owned resources used to automate traceability and consistency checks between design documents and requirements.
[DATA_EXFILTRATION]: While the skill reads sensitive project documentation (HLD/PRD), it does so for the purpose of local analysis and reporting. No evidence was found of instructions to transmit this data to unauthorized external endpoints.
[PROMPT_INJECTION]: The skill operates on a 'risk-driven' and 'evidence-based' model, explicitly instructing the agent to challenge the design based on documentation rather than overriding safety or system-level constraints.

hld-reviewer