game-cutscene-generator
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted user data to drive generation.
- Ingestion points: User-uploaded character reference sheets (e.g., hero.png) and text descriptions for location and lighting in SKILL.md.
- Boundary markers: The skill does not explicitly use delimiters to separate user data from instructions.
- Capability inventory: The skill triggers video generation models (Seedance, MiniMax) and audio tools (ElevenLabs MCP, Suno).
- Sanitization: No explicit input validation or sanitization of user-provided content is defined.
- Note: This risk is inherent to the skill's primary purpose of media generation based on user input and is considered a low-level structural observation rather than an active threat.
- [SAFE]: No malicious code, credentials, or exfiltration patterns were found. All external resource references trace back to the vendor's repository or well-known generative services.
Audit Metadata