03-refactor-legacy
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection surface identified through the skill's logic extraction and code mapping capabilities.
- Ingestion points: The skill reads and processes legacy WordPress plugin source files from user-defined paths (e.g.,
wp-content/plugins/). - Boundary markers: Absent. The instructions do not specify delimiters or provide instructions to ignore embedded commands or instructions found within the code or comments being refactored.
- Capability inventory: The skill performs file system scanning, mapping of hooks and functions, and extracts logic to write new PSR-4 compliant files in the
src/directory and updateconfig/Config.php. - Sanitization: Absent. There is no evidence of sanitization or filtering of the ingested code content before it is processed by the agent to generate new application logic.
Audit Metadata