blitzreels-editing
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
blitzreelsCLI tool for project editing tasks such astimeline cut,captions words list, andmedia attach. These operations are consistent with the vendor's intended functionality for media management. - [PROMPT_INJECTION]: While the skill processes external project data and caption text (representing an indirect prompt injection surface), the risk is minimized by instructions to use dry runs and perform visual verification of rendered frames before finalizing exports.
- Ingestion points: Project metadata, caption words, and media layers retrieved via REST API or CLI workspace.
- Boundary markers: None explicitly defined in the prompts.
- Capability inventory: Shell command execution via the
blitzreelsCLI and network mutations via REST API. - Sanitization: Visual verification of rendered frames and polling export success serve as functional verification steps.
Audit Metadata