ShareX Core Standards
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (HIGH): The skill requires the agent to execute shell commands (
dotnet build,git commit,git push) as part of its core workflow. The automation of the 'push' command is particularly risky as it allows for unreviewed code to be published to a remote server. - [PROMPT_INJECTION] (MEDIUM): The instructions use authoritative language ('CRITICAL', 'MUST') and specifically command the agent to 'Do not ask for permission' for external actions, which is an attempt to bypass the safety guidelines that usually require user confirmation for such operations.
Recommendations
- AI detected serious security threats
Audit Metadata