plugin-translations-update
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill presents an indirect prompt injection surface. Ingestion points: It reads .po and .pot files from the languages directory. Boundary markers: Absent; it does not define markers to separate untrusted translation data from agent instructions. Capability inventory: It executes npm and composer scripts and uses wp-cli. Sanitization: Absent; there is no mention of validating or escaping content read from translation files.
- [COMMAND_EXECUTION] (SAFE): The use of npm run build and composer run for translation tasks is standard practice and considered safe within the intended developer workflow.
Audit Metadata