directory-build-organization
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run standard .NET SDK commands such as
dotnet restore,dotnet build, anddotnet msbuild -pp:output.xml. These commands are used to validate the proposed configuration changes and inspect the preprocessed MSBuild output. - Evidence: Found in the 'Workflow' and 'Troubleshooting' sections of
SKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it is designed to ingest and audit untrusted user-provided project files (
.csproj,.sln,.proj). - Ingestion points: The agent is instructed to audit all project files across the solution (
SKILL.md, Workflow Step 1). - Boundary markers: The instructions include intent control guardrails (e.g., 'Do not create or edit files unless the user explicitly asks') but do not specify explicit delimiters for the parsed content.
- Capability inventory: The skill uses shell tools to execute
dotnetCLI commands for restoration and building (SKILL.md, Workflow Step 7). - Sanitization: No explicit sanitization or filtering of the ingested XML/project content is described before processing.
Audit Metadata