prompt-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (raw prompts or task descriptions) and interpolates it into the prompt generation process alongside external framework documentation. \n
- Ingestion points: User-provided content (Step 1) and local framework reference files (Step 3). \n
- Boundary markers: The workflow lacks specific delimiters or instructions to ignore embedded commands within the user's input. \n
- Capability inventory: The skill is limited to text generation; no high-risk tools such as shell commands, network utilities, or file-writing operations are invoked. \n
- Sanitization: No explicit validation or filtering of user-supplied strings is performed to mitigate potentially malicious instructions.
Audit Metadata