seedance-prompter
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by design as it transforms user-provided content into structured data for downstream AI processing.
- Ingestion points: User-provided creative intent and uploaded filenames (e.g., in SKILL.md examples) are directly interpolated into the 'final_prompt' field of the output JSON.
- Boundary markers: The skill lacks explicit boundary markers or instructions that would tell a downstream model to ignore malicious commands embedded within the user's creative description.
- Capability inventory: The skill itself contains no executable code, subprocess calls, or network operations, limiting the direct impact of an injection.
- Sanitization: There is no evidence of input validation, escaping, or sanitization of the user-provided text before it is formatted into the final prompt output.
Audit Metadata