dotnet-inspect-sourcelink
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches original source code from external URLs defined in SourceLink metadata. This data is ingested into the agent's context, creating a surface for indirect prompt injection if an attacker-controlled repository hosts source code with embedded instructions.
- Ingestion points: Network fetches from SourceLink URLs (e.g., raw GitHub content) triggered by the
Original Sourcecommand. - Boundary markers: No explicit delimiters or warnings to ignore instructions within the fetched code are defined in the skill instructions.
- Capability inventory: The skill environment executes the
dnx dotnet-inspectCLI tool. - Sanitization: There is no evidence of sanitization or filtering applied to the fetched source code before it is presented to the agent.
- [EXTERNAL_DOWNLOADS]: The skill is designed to perform network fetches to retrieve source files from remote providers. This is the primary intended purpose of the skill and is documented as such.
- [COMMAND_EXECUTION]: The skill invokes the
dnx dotnet-inspectcommand-line tool to process .NET assemblies and PDB files.
Audit Metadata