crap-score
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution: The skill instructs the agent to execute
dotnet testwith various coverage collection flags (e.g.,--collect:"XPlat Code Coverage"). This is a standard operation in .NET development environments to generate test results and code coverage data. - Indirect Prompt Injection Surface: The skill involves reading and parsing external data from
coverage.cobertura.xmlfiles,.csprojproject files, and C# source code. While this introduces a potential surface for indirect instruction, the skill's logic is focused on extracting numerical metrics (line-rate, cyclomatic complexity) for reporting purposes. - Ingestion points: Cobertura XML files and .NET source files (SKILL.md Step 2, Step 3).
- Boundary markers: None explicitly defined in the instructions for the parsed data.
- Capability inventory: Execution of
dotnetCLI commands (SKILL.md Step 1). - Sanitization: The skill does not explicitly define sanitization routines for the data parsed from XML or source files.
Audit Metadata