gc-minimal-zine-poster-v0-3
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a high-level instruction set for creative image generation. It does not contain any executable scripts, binary files, or commands that interact with the local filesystem or network in a malicious manner.
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests untrusted user content (themes, mood, article ideas) to generate prompts. However, this is categorized as safe due to the implementation of the 'Standard Mode Prompt Compiler,' which enforces rigid visual templates and negative constraints, effectively preventing the user from bypassing the agent's core instructions. Ingestion points: User-provided text and photos processed in the workflow described in SKILL.md. Boundary markers: None. Capability inventory: Uses the platform's built-in image generation tool. Sanitization: Inputs are mapped to specific visual paragraphs (Canvas, Attention Geometry, Image Anchor, etc.), limiting the influence of potentially malicious instructions.
Audit Metadata