wp-org-submission
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted WordPress plugin codebases, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads and analyzes user-supplied plugin source files (PHP, JS, CSS) and documentation (readme.txt) as part of the audit and submission workflow.
- Boundary markers: The instructions lack explicit delimiters or instructions to treat external plugin content as untrusted data or to ignore potential embedded instructions.
- Capability inventory: The agent can execute a shell script (scripts/svn-deploy.sh) that performs file system modifications via rsync and network operations via SVN.
- Sanitization: The skill does not implement automated validation or sanitization of the plugin code before processing.
- [COMMAND_EXECUTION]: The skill provides a shell script (scripts/svn-deploy.sh) to automate the synchronization of local build directories with remote SVN repositories. The script uses rsync and svn commands to manage deployment, which is a standard administrative capability but involves executing shell commands based on user-provided path and version arguments.
Audit Metadata