muapi-drone-style-video
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a standard wrapper for the MuAPI video generation service. It manages credentials securely via environment variables and interacts with the official service API at api.muapi.ai.
- [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface as it ingests untrusted user data (location_or_subject, style) and interpolates it into generation prompts without boundary markers or sanitization. This is associated with the primary purpose of the skill and relies on the downstream model's (Google Veo) safety filters for mitigation. * Ingestion points: User-provided inputs location_or_subject, shot_type, and style in SKILL.md. * Boundary markers: Absent; user input is directly concatenated into the prompt string. * Capability inventory: Executes video generation via muapi CLI or curl to external API endpoints. * Sanitization: No validation or escaping is performed on the user-provided text.
Audit Metadata