The Agent Skills Directory

[SAFE]: No malicious intent or high-risk security patterns were identified. The skill functions as a local productivity tool for gathering context for upcoming meetings.- [COMMAND_EXECUTION]: The skill utilizes the bash tool to run standard file system commands like grep, find, and head to retrieve information from a local Obsidian vault. These operations are constrained to the user's specified directory and do not involve privilege escalation.- [PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection because it processes untrusted data from local markdown files and presents it to the agent without boundary markers. * Ingestion points: Local markdown files retrieved during vault searches in SKILL.md (Steps 1, 2, and 3). * Boundary markers: Absent; file content is printed directly to the session context. * Capability inventory: Access to the bash shell and file system write access for saving briefs. * Sanitization: None; the skill does not escape or filter the content extracted from the notes.

meeting-prep-cc