dotnet-inspect
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
dnxutility to inspect .NET resources. - [INDIRECT_PROMPT_INJECTION]: The skill processes external .NET packages and assemblies, which constitutes a vulnerability surface where malicious metadata or code comments could attempt to influence the agent's behavior.
- Ingestion points: Untrusted external .NET packages, libraries, and source code specified in commands (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters to isolate external content from the agent's instructions.
- Capability inventory: Shell command execution via the
dnxutility. - Sanitization: No sanitization or validation of the inspected package content is performed within the skill instructions.
Audit Metadata