flux-3-video
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill defines a workflow that ingests untrusted data, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in media files.
- Ingestion points: The
flux-3-keyframes-continuationspecialist builds content from supplied images or video, as described inSKILL.md. - Boundary markers: None identified; the skill does not specify delimiters or instructions to ignore embedded content in processed media.
- Capability inventory: The
flux-3-generatespecialist performs technical submission and execution, as noted inSKILL.md. - Sanitization: No evidence of input sanitization, validation, or filtering for the supplied media is present in the instructions.
Audit Metadata