prompt-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided requirement descriptions, which represents a potential surface for indirect prompt injection attacks.
- Ingestion points: User input requirements are analyzed and transformed as described in the workflow in
SKILL.md. - Boundary markers: The instructions lack specific delimiters or boundary instructions to prevent the model from executing commands that might be embedded in the user requirements.
- Capability inventory: The skill is restricted to text generation and structured prompt optimization; it does not utilize any tools for file system access, network requests, or code execution.
- Sanitization: No explicit logic for sanitizing or filtering malicious instructions within the user-provided requirements is included in the methodology.
Audit Metadata