dotnet-core-expert
Fail
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow involves analyzing user-provided requirements to design and implement .NET solutions, which are then verified using local shell commands. This creates a surface where malicious instructions embedded in the requirements could lead to the generation and execution of harmful code during the build or test phase.\n
- Ingestion points: Analysis of user requirements and solution design steps in SKILL.md.\n
- Boundary markers: No specific delimiters or instructions to disregard embedded commands in the input requirements are provided.\n
- Capability inventory: Shell command execution via
dotnet buildanddotnet testas specified in the workflow in SKILL.md.\n - Sanitization: No validation or sanitization of input requirements is performed before they are used to generate implementation code.\n- [COMMAND_EXECUTION]: The workflow requires the agent to execute shell commands such as
dotnet build,dotnet test, andcurl. While standard for a developer-focused skill, these commands execute code within the agent's environment.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation athttps://jeffallan.github.io/claude-skills/skills/backend/dotnet-core-expert/. This URL is part of the author's official documentation infrastructure on a well-known service.
Recommendations
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata