azure-logic-apps
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill is authored by a trusted vendor (microsoftdocs) and exclusively references official Microsoft domains (learn.microsoft.com) and repositories. All recommended tools and resources are within the vendor's verified ecosystem.
- [INDIRECT_PROMPT_INJECTION]: The skill involves fetching and processing external documentation, which creates a data ingestion surface. This is assessed as safe because the sources are restricted to authoritative technical documentation from a trusted domain.
- Ingestion points: Markdown documentation retrieved from learn.microsoft.com using specified fetch tools.
- Boundary markers: None explicitly defined in the skill markdown body.
- Capability inventory: The skill is limited to documentation retrieval; no high-risk capabilities such as arbitrary shell execution, persistent storage modification, or network exfiltration were found.
- Sanitization: Content is fetched from a trusted source; no specific sanitization or filtering logic is implemented within the skill definition.
- [EXTERNAL_DOWNLOADS]: The skill contains a categorized list of links to Azure documentation. All URLs were verified to point to official Microsoft properties, representing standard knowledge retrieval functionality.
Audit Metadata