creative-tool-scout
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to research external sources including official documentation, repositories, and developer showcases. These third-party sites are ingestion points for untrusted data which could contain malicious instructions (indirect prompt injection). However, the skill itself lacks capabilities like file system modifications or shell command execution, which significantly mitigates the risk.
- [EXTERNAL_DOWNLOADS]: The skill references several external documentation sites and public repositories for research purposes, including those from Remotion, HeyGen, Lottie, and Rive. These references are documented neutrally as resources for technical comparison and do not involve automated installation or execution of remote code.
- [SAFE]: The process includes explicit safety checks, such as advising the agent to report unavailable capabilities if a host lacks an authorized native app/bridge rather than attempting to install one or claiming success.
Audit Metadata