Find or connect an Azure application's or Foundry agent's telemetry for an explicit observability, monitoring, alerting, health or operational diagnosis request. Confirm source scope and task-specific telemetry access; not generic app connection, resource creation or deployment readiness. Instrumentation/collection design can precede deployment; answer conceptual questions directly. No automatic provisioning or changes.
81%
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 canonical home for this skill is connect-observability in microsoft/GitHub-Copilot-for-Azure
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 required workflow runs bounded KQL/metric/trace reads against the developer's confirmed Application Insights or Log Analytics sources, and public traffic to the monitored app can write attacker-chosen strings (request fields, exception messages, span names) into those tables, so the agent can ingest that text without the developer selecting any specific item.
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.