wp-plugin-development
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Node.js scripts (
detect_wp_project.mjsanddetect_plugins.mjs) to automate the detection of WordPress projects and plugin structures within the working directory. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by reading and processing untrusted data from local WordPress project files and plugin headers.
- Ingestion points: Project files and plugin headers are scanned during the triage and detection phases described in
SKILL.md. - Boundary markers: Absent; the instructions do not define specific delimiters or instructions to ignore embedded prompts when reading project files.
- Capability inventory: The skill has capabilities for subprocess execution (via
node) and file system operations (creating and refactoring plugin code). - Sanitization: Absent; there is no explicit validation or sanitization of the content extracted from the project files before it enters the agent's context.
Audit Metadata