umbraco-add-extension-reference

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Command Execution] (SAFE): The skill uses the 'Bash' tool specifically to run 'dotnet sln add', which is a legitimate project management command. No evidence of arbitrary command injection or privilege escalation was found.\n- [Data Exfiltration] (SAFE): The skill only interacts with local project files and does not use any network-enabled tools like curl or wget. It does not access sensitive system locations.\n- [Prompt Injection] (SAFE): There are no instructions in the skill aimed at bypassing AI safety protocols or extracting system prompts.\n- [Indirect Prompt Injection] (SAFE): While the skill processes local project files (ingestion points: Glob/Read on .csproj and .sln), which technically constitutes an attack surface, the operations are limited to structured XML/SLN editing. Capability inventory: Edit and Bash (dotnet). Boundary markers and sanitization are absent, but the risk is negligible for the intended use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:59 PM