azure-update-manager
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a legitimate knowledge base for Azure Update Manager, referencing official Microsoft domains and tools for documentation retrieval.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data from
learn.microsoft.com. While this creates a potential surface for indirect prompt injection, it is considered safe due to the trusted nature of the target domain and the absence of any exploitable capabilities like file system modification or process execution in the skill definition. - Ingestion points:
SKILL.md(via external learning URLs used for fetching documentation) - Boundary markers: Absent in the skill instructions
- Capability inventory: None (no code or shell execution tools defined in this skill)
- Sanitization: Absent
Audit Metadata