The Agent Skills Directory

[SAFE]: The skill performs routine file management within a user's personal vault, specifically reading and creating markdown notes. No evidence of remote code execution, credential harvesting, or unauthorized network activity was detected. The logic focuses on productivity workflows and provides clear troubleshooting steps for expected environment issues.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from local directories.
Ingestion points: The skill reads contents from daily/, projects/, and inbox/ folders to generate briefings and carry forward tasks (SKILL.md, Steps 1-3).
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the briefing interpolation logic.
Capability inventory: The skill's capabilities are restricted to reading local files and writing new markdown notes. It lacks tools for network communication, shell command execution, or system modification.
Sanitization: Content extracted from existing notes is interpolated directly into the morning briefing and new daily notes without sanitization. However, due to the limited capabilities of the skill, the risk is minimal.

daily