The Agent Skills Directory

[SAFE]: No security issues were detected. The skill consists of Markdown-based instructions and templates for legal analysis.
[PROMPT_INJECTION]: The skill uses structural constraints (e.g., 'Mandatory Constraints', 'Boundaries') to guide agent behavior towards accuracy and professional neutrality. No malicious override or bypass patterns were found.
[DATA_EXFILTRATION]: There are no network-capable tools or commands (like curl or wget) and no access to sensitive file paths.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts or packages.
[COMMAND_EXECUTION]: The instructions do not involve any shell commands or subprocess execution.
[INDIRECT_PROMPT_INJECTION]: While the skill processes external data (statutory text and scenarios), it implements strong boundary markers. It requires verbatim quotations, block markers, and a 'Separation of Layers' between quoted text and explanation, which mitigates the risk of instructions in the statutory text influencing the agent.

statute-briefer