The Agent Skills Directory

[SAFE]: No malicious behavior, obfuscation, or data exfiltration patterns were detected.
[COMMAND_EXECUTION]: The skill uses a local command-line tool, minutes, to retrieve meeting data. This is consistent with the skill's stated purpose and is restricted to the local environment.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it reads and displays data from external files. 1. Ingestion points: Files with .md extension in ~/vault/meetings/ (SKILL.md). 2. Boundary markers: No specific delimiters or ignore instructions are present. 3. Capability inventory: Uses minutes list to display meeting metadata (SKILL.md). 4. Sanitization: No explicit sanitization of the meeting file content is performed before presentation to the agent.

meetings-list