apex-client-browser-audit
Use when the user asks to "audit PM tools visually", "inspect Jira configuration", "review Azure DevOps setup", "check Monday.com boards", or "evaluate tool configuration". Activates when a stakeholder needs to perform a visual audit of PM tool configurations, capture screenshot evidence of misconfigurations, compare tool setup against methodology best practices, identify workflow anti-patterns in PM tools, or produce a remediation roadmap for tool optimization.
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
The agent visits user-specified PM tool URLs (such as Jira or Azure DevOps) via MCP Playwright, where rendered web pages and outsider-authored ticket/board content are ingested during visual audits.
- Repository
JaviMontano/mao-discovery-framework
- Revision
15f6e4a
- 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.