dotnet-modernize
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes shell commands to scan and ingest content from local project files, creating a surface for indirect instructions to influence the agent context.\n
- Ingestion points: The skill reads contents and filenames from .csproj, .cs, .props, and appsettings.json files within the target project directory via find and grep commands.\n
- Boundary markers: Absent. There are no explicit markers or instructions defined to isolate the ingested file content from the agent's control flow or to warn the agent against following embedded instructions.\n
- Capability inventory: The skill performs file system reads and utilizes the dotnet CLI for package auditing, providing a path for extracted data to reach the agent's decision-making logic.\n
- Sanitization: Absent. The results of shell-based scans are directly presented to the agent without filtering or sanitizing the content for potentially malicious prompt injection strings.
Audit Metadata