The Agent Skills Directory

[Data Exposure & Exfiltration] (SAFE): The skill uses standard file manipulation tools (Read, Write, Edit) but lacks any network connectivity or exfiltration vectors. Access is intended for internal documentation paths.
[Remote Code Execution] (SAFE): No external dependencies, package managers, or remote script execution patterns were detected.
[Indirect Prompt Injection] (LOW): The skill has a data ingestion surface through tools like Read and Grep. While it could potentially process malicious instructions embedded in documents, it lacks high-risk capabilities (like network access or arbitrary command execution) that would allow for significant impact from such an injection.
[Metadata Poisoning] (SAFE): Metadata fields are descriptive and consistent with the skill's primary purpose of documentation management.
[No Code] (SAFE): No scripts (.py, .js, .sh) or binaries are included with this skill; it consists entirely of declarative instructions.

docs-internal