prompt-optimizer

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user data to generate optimized prompts, creating a surface for indirect prompt injection.
  • Ingestion points: User prompts are ingested in SKILL.md for analysis and transformation.
  • Boundary markers: The skill lacks explicit delimiters or instructions to ignore malicious commands embedded within the user's original prompt.
  • Capability inventory: The skill utilizes the AskUserQuestion tool to interact with users and outputs revised prompts.
  • Sanitization: There is no evidence of input validation or sanitization to prevent the propagation of malicious instructions from the source prompt to the optimized output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 01:38 PM