azure-aks-edge-essentials
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to retrieve technical documentation from official Microsoft domains (
learn.microsoft.com) using tools likemcp_microsoftdocs:microsoft_docs_fetch. These references are to a well-known service and are considered legitimate. - [INDIRECT_PROMPT_INJECTION]: This skill possesses an attack surface for indirect prompt injection as it ingests remote markdown data.
- Ingestion points: Remote documentation URLs listed throughout
SKILL.mdare fetched into the agent's context at runtime. - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided in the current skill file.
- Capability inventory: The skill provides informational capabilities; no subprocess execution, sensitive file system access, or network write capabilities are defined within this skill package.
- Sanitization: No validation or sanitization logic is present for the fetched documentation content.
- [SAFE]: The skill contains no executable scripts, hardcoded credentials, or persistence mechanisms. Its functionality is limited to acting as a technical reference guide pointing to a trusted vendor's infrastructure.
Audit Metadata