verify-visual-review
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and serves a benign purpose for visual design quality assurance. No malicious patterns such as code obfuscation or remote code execution were identified.
- [DATA_EXFILTRATION]: The skill does not contain any hardcoded credentials, sensitive file path accesses, or instructions to send data to external servers. All referenced paths are placeholders for local visual artifacts.
- [PROMPT_INJECTION]: The skill involves reviewing external files (PDFs, images, decks), which presents a potential surface for indirect prompt injection. However, the instructions are strictly focused on visual metrics such as alignment, contrast, and hierarchy, and the skill does not grant the agent dangerous capabilities like network access or shell execution that could be exploited via these files.
- [COMMAND_EXECUTION]: There are no shell commands, remote scripts, or dynamic code execution patterns present in the file. All operations are limited to reading visual properties of artifacts.
Audit Metadata