workflow-foundation
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by inspecting repository files and designer artifacts to assess legacy workflow logic. This creates a surface for processing untrusted data that might contain embedded instructions.\n
- Ingestion points: Repository context and source files as indicated in the
SKILL.mddescription and workflow steps.\n - Boundary markers: Explicit delimiters or instructions to ignore embedded commands in the source data are not present.\n
- Capability inventory: The skill description indicates permissions to edit targeted files and execute build, test, lint, or validation commands.\n
- Sanitization: No specific content sanitization or validation protocols for the repository files are mentioned.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation and project repositories from Microsoft's official Learn site, the Azure GitHub organization, and established open-source projects including Elsa Workflows and MassTransit.\n- [COMMAND_EXECUTION]: The skill allows for the execution of build and validation commands to verify the integrity of legacy process logic during maintenance or migration phases.
Audit Metadata