morphir-architect

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's architectural review capability introduces a surface for indirect prompt injection by processing external source code.
  • Ingestion points: The skill reads project source files including F# (.fs, .fsx) and C# (.cs) files from the src/ directory and script folders.
  • Boundary markers: The instructions lack explicit boundary markers or directives to ignore embedded instructions within the analyzed code content.
  • Capability inventory: The agent is authorized to execute shell commands using the dotnet CLI, specifically for building, formatting, and running scripts.
  • Sanitization: No sanitization or validation of the analyzed file content is specified before processing.
  • [COMMAND_EXECUTION]: The skill requires the execution of several shell-based commands and local scripts to perform its primary functions.
  • Evidence: The skill instructs the agent to run 'dotnet fsi .claude/skills/morphir-architect/scripts/architecture-review.fsx', 'dotnet build', and 'dotnet format'.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:45 PM