umbraco-add-extension-reference

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill discovers and reads project files (.csproj, .sln) from the local workspace to determine project structure. Ingestion points: Workspace files accessed via Glob and Read tools. Boundary markers: None present; the skill assumes valid project XML structure. Capability inventory: Uses Edit for file modification and Bash for command execution. Sanitization: Content from project files is interpolated into XML and shell commands without explicit sanitization.
  • [COMMAND_EXECUTION]: The skill uses Bash to execute dotnet sln add using paths discovered in the workspace. While this is a standard project management task, it relies on file paths that could be manipulated in a malicious workspace.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:59 AM
Security Audit — agent-trust-hub — umbraco-add-extension-reference