handdrawn-live-video-generator
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses natural instructional language to guide the AI in generating video prompts. No attempts to bypass safety filters, extract system prompts, or override agent constraints were found.
- [DATA_EXFILTRATION]: No sensitive file paths, credential markers, or suspicious network operations were identified. The skill operates within the context of generating text prompts and recommending specific video models.
- [OBFUSCATION]: The content was scanned for Base64 encoding, zero-width characters, homoglyphs, and hidden text patterns. All content is clear-text and readable.
- [REMOTE_CODE_EXECUTION]: There are no package installations, script downloads, or dynamic code execution patterns. The skill relies on standard model interactions.
- [PRIVILEGE_ESCALATION]: No commands related to system permissions, administrative access, or persistence mechanisms (like cron jobs or startup scripts) were detected.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied scene ideas and moods, its capabilities are restricted to text generation and model recommendation. It lacks high-risk capabilities like file system writes or arbitrary command execution that would make it vulnerable to exploitation via indirect injection.
Audit Metadata