avatar-video
Fail
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from multiple sources, including user-provided scripts, template variables, and webhook payloads. It lacks specific boundary markers or sanitization instructions to prevent instructions embedded within this data from influencing the agent's downstream reasoning or tool use.
- [DYNAMIC_EXECUTION]: The integration workflow for Remotion involves bundling and rendering local source code at runtime. This creates a surface where an attacker could potentially influence the build or rendering process by injecting malicious content into the project files processed by the Remotion bundler.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata