image
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides purely instructional content for visual content production, AI image prompting, and web optimization.
- [SAFE]: The shell commands provided for image optimization (cwebp, mogrify, jpegoptim) and checking image sources (curl) are standard utilities for web development and do not exhibit malicious intent or exfiltration patterns.
- [SAFE]: The skill references and recommends libraries and services from well-known providers such as Vercel, Google, and OpenAI.
- [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read local strategy and brand guidelines files (e.g.,
.agents/marketing-strategy.md). This represents a data ingestion surface; however, this behavior is a core functional requirement for the skill to provide brand-consistent output and is considered a safe practice in this context.
Audit Metadata