The Agent Skills Directory

[NO_CODE]: The skill consists entirely of high-level instructions and architectural descriptions without any embedded scripts or executable code.
[SAFE]: No malicious patterns, such as obfuscation, credential harvesting, or unauthorized network access, were found. The skill operates as a logical coordinator for other tasks.
[COMMAND_EXECUTION]: The workflow involves creating and saving files to the .omc/specs/ directory. This activity is local and consistent with the skill's role in documentation and requirements management.
[PROMPT_INJECTION]: The use of terminology like "injection" and "overrides" in the documentation refers to the architectural data flow between pipeline stages (passing investigation findings to the interview phase) rather than attempts to bypass AI safety guardrails.

deep-dive