agent-smith
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions and a bundled PowerShell script (
scripts/repair-roslyn-multiproject-artifacts.ps1) for identifying and repairing specific Roslyn multi-project merge artifacts. The execution is scoped to local repository files and includes a check mode to prevent unintended modifications.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code and configuration files from the user's repository. This creates a surface where instructions embedded in those files could theoretically influence the agent's behavior. However, the skill mitigates this through a structured workflow that requires evidence-based validation, build verification, and automated testing before completion.
Audit Metadata