prompt-optimizer
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-supplied prompts as its primary input to generate optimized recommendations.
- [PROMPT_INJECTION]: Ingestion points: Raw user prompts and draft text provided for optimization are processed in Phase 1 and Phase 4 (SKILL.md).
- [PROMPT_INJECTION]: Boundary markers: Absent; the output format defined for optimized prompts does not include delimiters or instructions to the model to ignore potentially malicious instructions within the user-provided draft.
- [PROMPT_INJECTION]: Capability inventory: The skill is restricted to an advisory role and is forbidden from writing code, creating files, or executing system commands (SKILL.md).
- [PROMPT_INJECTION]: Sanitization: Absent; the skill does not perform validation or filtering of user-supplied input before incorporating it into the final optimized output.
Audit Metadata