microsoft-skill-creator

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download the official Microsoft Learn CLI tool (@microsoft/learn-cli) from the npm registry.
  • [COMMAND_EXECUTION]: The skill uses shell commands via the mslearn CLI to perform documentation searches and fetch page content.
  • [REMOTE_CODE_EXECUTION]: The skill downloads and executes the @microsoft/learn-cli package from a remote registry using npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection when processing documentation. 1. Ingestion points: microsoft_docs_search and microsoft_docs_fetch in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Generates skill files, directory structures, and code samples based on fetched documentation. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 08:18 AM