Google Meet through gog. Use for Google Meet spaces, configuration, call history, and participants.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The `participants` command reads display names of people who joined a meeting the agent selected, and external attendees can set those names, so outsider-authored text reaches the agent only after the agent picks a specific meeting, which fits the low category.
openclaw/gogcli
6d97417
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.