The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized access behaviors were detected.
[EXTERNAL_DOWNLOADS]: The skill fetches capability configurations and operation schemas from the official vendor domain at blitzreels.com.
[COMMAND_EXECUTION]: Media production tasks are orchestrated using the vendor-specific blitzreels CLI (e.g., blitzreels projects create, blitzreels faceless plans approve), which is consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill processes user-supplied topics and scripts to generate narration and visual prompts. While this creates a surface for indirect prompt injection, the risk is mitigated by a multi-stage approval process requiring human review of the plan, cost, assets, and final timeline.
Ingestion points: User-provided topics, scripts, and production briefs in SKILL.md.
Boundary markers: None present; the system relies on procedural checkpoints.
Capability inventory: Project management and media generation via the blitzreels CLI and REST endpoints described in references/faceless-workflow.md.
Sanitization: Risk is mitigated through manual approval gates (Steps 6, 7, 8, and 9 in SKILL.md) that require verification of plans and assets before finalizing production.

blitzreels-generation