imagegen-frontend-web
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language art direction guidelines and configuration defaults for image generation. No scripts, binaries, or command-line execution patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided design briefs to influence its output. While this constitutes a surface for indirect prompt injection, the skill lacks any capabilities (such as shell access, file writing, or network requests) that would make such a surface exploitable for malicious purposes.
- Ingestion points: SKILL.md (processes user-provided briefs through the primary prompt).
- Boundary markers: The instructions prioritize user briefs but do not define strict delimiters or sanitization protocols for the input.
- Capability inventory: None. The skill only outputs text directives for image generation.
- Sanitization: None detected.
Audit Metadata