kraft-stencil-landmark
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill consists of prompt instructions and configuration files for an image generation task.
- [NO_CODE]: The skill does not contain any executable scripts, binaries, or command execution patterns.
- [INDIRECT_PROMPT_INJECTION]: Analysis of the data ingestion surface shows no exploitable capabilities. 1. Ingestion points: User-provided images (SKILL.md). 2. Boundary markers: Instructions explicitly restrict content to the source image and forbid external additions like URLs or logos. 3. Capability inventory: None. No network, file, or shell access requested or used. 4. Sanitization: Not applicable as no code is executed on inputs.
Audit Metadata