title-craft
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security vulnerabilities identified. The skill content consists of static instructions, templates, and principles for text generation.\n- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes user-provided video topics and reads a local configuration file (.agents/youtube-context.md). Because the skill lacks tool-use capabilities such as network access, file system modification, or command execution, this surface does not present a path for exploitation.
Audit Metadata