logo-creator
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute several local Python scripts for core functionality:
scripts/compose_logo.py: Orchestrates logo composition by combining symbols and text.scripts/remove_bg.py: A local fallback for AI-driven background removal.scripts/create_logo_sheet.py: Generates HTML contact sheets for visual review.- [EXTERNAL_DOWNLOADS]: The skill facilitates the download of external resources from trusted and well-known services:
- Fetches typography dynamically from Google Fonts (
fonts.googleapis.com) during the logo composition process. - Requires the installation of the Playwright browser automation framework and associated browser binaries.
- Downloads pre-trained AI models for background removal when using the
rembglibrary. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes untrusted data from external sources:
- Ingestion points: Brand research is conducted via
web-searchandimage-search, with results being synthesized to guide design directions (SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following malicious instructions found within search results.
- Capability inventory: The agent has the capability to execute shell scripts and generate images based on processed data.
- Sanitization: The skill does not implement specific sanitization or filtering for search results before they influence subsequent agent actions.
Audit Metadata