join-meeting
AgentCall (agentcall.dev) — Join a video meeting (Google Meet, Teams, Zoom) as an AI bot with voice and visual presence. Supports audio-only mode with voice intelligence (barge-in, interruptions), text-to-speech mode, and webpage modes for custom UI. Use when asked to join a call, attend a meeting, or participate in a video conference.
68
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill instructs the agent to "ask the user for their API key" and shows a here-doc command to write the key into ~/.agentcall/config.json, which requires the LLM to accept and/or embed the secret verbatim in commands or code (exfiltration risk).
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
In `SKILL.md` the required runtime loop ingests outsider-authored meeting text via `transcript.final`/`chat.received` events (and corresponding `user.message` in bridge-style) and feeds it to the agent for response/processing, meaning any participant can inject free text into the agent’s context.
- Repository
- pattern-ai-labs/agentcall
- Path
SKILL.md
- Commit
7b0841e
- Audited
- Security analysis
Is this your skill?
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.