The Agent Skills Directory

[SAFE]: The skill is comprised entirely of instructional text and configuration files. It contains no scripts, binaries, or executable code, eliminating the risk of direct malicious execution.- [NO_CODE]: No code files, package dependencies, or external scripts are included or referenced.- [PROMPT_INJECTION]: Analysis of the instructions revealed no attempts to bypass safety filters, extract system prompts, or override agent constraints. The skill explicitly reinforces adherence to safety protocols by stating that work should stop if 'safety or policy prevents continuation'.- [DATA_EXFILTRATION]: There are no network operations, API calls, or commands that access sensitive file paths. The skill does not possess any mechanism for transmitting data to external domains.- [COMMAND_EXECUTION]: No shell commands, subprocess invocations, or system-level operations are present in the skill instructions.

nd-goal-persistence