team-group-photo
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the bun runtime to execute local TypeScript scripts for style selection, image generation, and optimization. These scripts are located within the plugin's local directory structure as referenced by the CLAUDE_PLUGIN_ROOT variable.
- [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it incorporates user-supplied names and background preferences directly into prompts for image generation. * Ingestion points: User-provided names and background descriptions collected in Step 1 of SKILL.md. * Boundary markers: No specific delimiters or safety warnings are present to isolate user-provided text from the instruction prompt. * Capability inventory: The skill is capable of executing command-line utilities for image processing and local file management. * Sanitization: There is no evidence of sanitization or validation performed on user-provided strings before they are used as arguments for script execution.
Audit Metadata