talk-firtman-web-mcp-agentic-web
Use when the user asks about Maximiliano Firtman's ("Maxi") AI Native DevCon talk on Web MCP and the agentic web — including questions about how Web MCP differs from MCP, exposing frontend tools to AI agents, the imperative vs declarative Web MCP APIs, tool design guidance (name/description/input schema/execute), the Chrome 149 origin trial, using Chrome DevTools MCP or Puppeteer as a bridge today, the Doom demo, or applying Firtman's "pick one high-value page state" adoption approach to current work.
71
89%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
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 repeatedly requires the model to quote verbatim from transcript.md (and include those verbatim quotes in outputs), so if transcript.md contains any secrets/tokens the model is explicitly instructed to emit them verbatim — creating an 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
Skill.md outlines a Web MCP approach where a Web MCP tool’s execute function is run by an agent using the frontend/browser context, meaning outsider-authored free text in the monitored web UI (e.g., form fields or page content provided by third parties) could be ingested via that page state before any explicit tool-selection gate.
- Repository
- AINativeDev/aidevcon-2026-ldn
- Commit
df83a42
- 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.