veo-cinematic-reels
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Node.js utility script (
scripts/scene-prompts.mjs) used to automate the generation of video prompts from a JSON-formatted plan. The script performs local file read/write operations using built-in Node.js modules and follows the author's branding ('deepak-skill'). No suspicious network calls or unauthorized file access patterns were found within this script. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data in
scene-plan.jsonto assemble video generation prompts. - Ingestion points: The
scripts/scene-prompts.mjsscript reads content from a user-provided JSON file. - Boundary markers: Absent. The script performs direct string interpolation of plan data into the final prompt text.
- Capability inventory: The skill performs file system read and write operations locally.
- Sanitization: None. The script assumes the JSON input is trusted and correctly formatted for prompt generation.
- [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The skill's behavior is consistent with its stated purpose of assisting in cinematic video production.
Audit Metadata