sketch-image-prompt
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill instructions or workflow.
- [PROMPT_INJECTION]: The instructions are focused on formatting and stylistic transformation. There are no attempts to bypass safety filters or override system instructions.
- [REMOTE_CODE_EXECUTION]: The skill does not contain any scripts, package requirements, or commands to download or execute external code.
- [DATA_EXFILTRATION]: There are no network operations, and the skill does not attempt to access sensitive local files or environment variables.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted user-provided articles (ingestion point), it has no dangerous capabilities (capability inventory limited to text generation). There are no specific boundary markers for the input text, but the output is restricted to a specific image prompt format, posing no functional risk.
Audit Metadata