blitzreels-carousels
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized system access attempts were found in the skill instructions or evaluation files.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts and external image URLs to generate carousel content. While this is an ingestion surface for indirect prompt injection, it is the primary purpose of the skill and lacks access to dangerous tools or sensitive data. Evidence: (1) Ingestion: User workflow inputs in SKILL.md and image URLs in evals/evals.json. (2) Boundaries: Absent. (3) Capabilities: Project management, job polling, and media export to ZIP. (4) Sanitization: Not specified.
Audit Metadata