slide-visual-selector
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches design tokens and configuration data from the vendor's official domain.
- Evidence:
https://zynkr.ai/data/tokens.jsonis referenced inreferences/brand-source.mdto retrieve color values. - [COMMAND_EXECUTION]: The installation instructions utilize a shell command to fetch and add the skill from the author's repository.
- Evidence:
npx skills add https://github.com/peter-tu-zynkr/zynkr-skill-builder --skill slide-visual-selectorinSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill ingests natural language content from upstream relay packets and external brand guides to influence its visual selection logic.
- Ingestion points: The skill reads
SLIDE_PACKET ▸ Pagesfrom theslide-page-splitterskill and fetches brand standards from Google Drive using platform-provided tools. - Boundary markers: No specific delimiters or boundary instructions are used to separate untrusted data from the core instructions.
- Capability inventory: The skill possesses file-reading capabilities, uses the
google-workspacetoolset, and relays processed data to a downstream rendering skill (slide-pptx). - Sanitization: There is no evidence of filtering or sanitization performed on the ingested content before it is used to determine layout archetypes.
Audit Metadata