cms-gallery-builder
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could contain malicious instructions.
- Ingestion points: User-provided
title,description, andimage(URL or base64) defined in the Input contract section of SKILL.md. - Boundary markers: No specific delimiters or "ignore" instructions are defined for interpolating user metadata into tool calls.
- Capability inventory: The skill utilizes
cms_create_photosandcms_update_phototo create and modify CMS content. - Sanitization: No explicit sanitization or validation of the input metadata is specified in the workflow.
- Mitigation: The risk is significantly reduced by the mandatory "Preview (dry-run)" step that requires explicit user confirmation before any upload or update occurs.
Audit Metadata