english-prompt-optimizer

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8).
  • Ingestion points: Untrusted user input is ingested during the language detection and translation workflow described in Step 1 and Step 2.
  • Boundary markers: The skill uses triple dashes (---) to delimit the 'Optimized Prompt' but does not include instructions to the agent to ignore any commands embedded within the translated text.
  • Capability inventory: The 'Step 4: Execute' phase grants the agent the capability to process the optimized English prompt as a direct command set, which could be exploited by a malicious non-English input.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the user's original input or the resulting translation before it is executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 02:35 PM