other
- Location
SKILL.md:193- Finding
Explicit Content-Filter Circumvention Guidance
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 193–198
Vulnerability Type: Content Safety Filter Circumvention
Risk Level: MediumComplete Snippet:
markdown **Dezgo Content Policy (Stand 28.07.2026):** | API | Content-Filter | |---|---| | Flux TXT2IMG | Kein Filter – alle Prompts erlaubt | | SDXL/SD1.5/SDXL2 TXT2IMG | Standard Dezgo-Filter | | **Image-Tools** (I2I, Inpainting, RemoveBG, Upscale, Edit, ControlNet) | Dezgo blockt bestimmte Prompts (HTTP 500) | **Workaround für restriktive Prompts:** - Flux TXT2IMG mit direktem Prompt (kein Filter)Technical Analysis
The Skill identifies Flux TXT2IMG as an unfiltered route where all prompts are accepted and explicitly recommends it as a workaround for prompts restricted by other Dezgo endpoints. This creates a documented method for circumventing upstream content controls.
The same behavior is reinforced at lines 47 and 207, where Flux is advertised as “uncensored.” This issue does not qualify as skill instruction hijacking because the Skill does not attempt to alter the Agent's governing instructions, role, or safety hierarchy. It is instead a content-safety circumvention issue outside the listed T01–T09 classifications.
Attack Path
- A user submits an image-generation prompt prohibited by a filtered Dezgo model.
- The filtered endpoint rejects or blocks the prompt.
- The Agent consults the Skill and follows its documented workaround.
- The Agent resubmits the restricted prompt directly through the unfiltered Flux TXT2IMG category.
- The service may generate content that the filtered endpoint was intended to prevent.
Impact Assessment
Exploitation does not grant operating-system privileges, code execution, persistent access, or access to credentials. Its scope is the image-generation service and the content it can produce. A user may bypass model-level filtering and potentially generate restricted imagery, ...[truncated 77 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove the recommendation to route restricted prompts through an unfiltered model.
- Replace “all prompts allowed” and “uncensored” language with a clear acceptable-use policy.
- Require policy validation before requests are submitted, regardless of the selected model or upstream filtering behavior.
- Treat an upstream content-policy rejection as final rather than retrying the prompt through a less restrictive endpoint.
- Apply consistent server-side moderation to every generation category, including Flux.
- Record rejected requests and model-routing decisions for abuse monitoring without retaining unnecessary sensitive prompt or image data.
- Document that the Agent's governing safety requirements remain applicable even when an upstream model does not enforce equivalent filters.
