The Agent Skills Directory

[SAFE]: The skill's primary function is to aggregate information from authorized enterprise tools (Google Calendar, Fireflies, Slack, Jira, Gmail, and Confluence) to provide a meeting brief. All data access is performed through standard tool integrations.
[DATA_EXFILTRATION]: No evidence of data exfiltration was found. The instructions explicitly state that output is shown in chat only and never written elsewhere. No external network requests to third-party domains (other than the standard tool APIs) are present.
[PROMPT_INJECTION]: The skill includes trigger phrases in English and Polish to initiate meeting preparation but does not contain instructions to bypass safety filters or override the agent's core instructions.
[COMMAND_EXECUTION]: The skill does not utilize shell commands or perform any unauthorized file system operations. It operates entirely within the scope of the provided tool environment.
[REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of external scripts or packages.
[SAFE]: The skill includes a clear distinction between sourced data and AI-inferred suggestions (using the '💡 suggested:' label), which is a best practice for transparency and accuracy in AI-generated summaries.

meetings-prep