seedream-image
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and metadata. No scripts, binaries, or executable files are included.
- [EXTERNAL_DOWNLOADS] (SAFE): External links are provided for documentation and platform access (e.g., Jimeng AI, Volcengine Ark) and are used for informational purposes only. No automated downloads or script executions are performed.
- [PROMPT_INJECTION] (SAFE): No malicious instructions aimed at bypassing agent safety filters, overriding core behavior, or extracting system prompts were detected. The content is focused on structured prompt generation.
- [DATA_EXFILTRATION] (SAFE): No commands or logic for accessing sensitive files (credentials, SSH keys) or exfiltrating data to external domains were found.
- [INDIRECT_PROMPT_INJECTION] (LOW): While the skill processes user-provided inputs to generate prompts (e.g., product descriptions, names), it lacks any executable capabilities or network-writing functions that could be exploited by malicious input data.
Audit Metadata