wordpress-router
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the execution of both a fixed triage script and variable commands found within the codebase.
- Execution of a local Node.js script:
node skills/wp-project-triage/scripts/detect_wp_project.mjs. - Instruction to run repo-specific lint, test, and build commands identified during the triage process.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external repository data that can influence agent behavior and command execution.
- Ingestion points: Processes repository metadata and configuration files including
composer.json,package.json,style.css,block.json,theme.json, and thewp-content/directory. - Boundary markers: The instructions do not define boundaries or warn the agent to ignore potentially malicious instructions embedded in the project files.
- Capability inventory: The agent is authorized to execute Node.js scripts and arbitrary shell commands defined in the project's build or test configurations.
- Sanitization: There is no evidence of validation or sanitization of the commands suggested by the repository's configuration before they are executed.
Audit Metadata