The Agent Skills Directory

[SAFE]: The skill is designed to manage writing projects locally using standard file operations. It does not perform network operations, execute remote code, or request elevated privileges. All functionality is consistent with the stated purpose of tracking manuscript progress.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads and processes user-controlled content from files like project.yaml and premise.md. However, its capabilities are restricted to local file operations within a scoped project directory, significantly limiting the potential impact of such an attack.
Ingestion points: Markdown and YAML files stored in the projects/ directory (SKILL.md).
Boundary markers: Absent; there are no specific instructions to the agent to disregard instructions embedded within project data.
Capability inventory: Restricted to file:read and file:write permissions.
Sanitization: The skill does not include instructions for sanitizing or validating the content of the manuscript files before processing them.

manuscript-hub