The Agent Skills Directory

[SAFE]: No evidence of malicious intent, data exfiltration, or unauthorized command execution was found within the skill files.
[PROMPT_INJECTION]: The skill instructions are focused entirely on the functional task of legal document generation. There are no attempts to override agent safety protocols or bypass system constraints.
[REMOTE_CODE_EXECUTION]: The skill does not perform remote downloads or execute scripts from external or untrusted sources. All references are to local directories within the skill environment.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests untrusted data during the interview process defined in ./scripts/interview.md.
Boundary markers: The provided files do not specify explicit boundary markers or sanitization logic for the user-provided legal details.
Capability inventory: The skill has the capability to write multiple .mdx and .tsx files to the src/ directory of the host project.
Sanitization: Not specified in the metadata. While this represents a standard data ingestion surface, it is necessary for the skill's primary purpose and does not present an immediate threat without evidence of malicious exploitation patterns.

privacy-global