baoyu-image-gen
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads content from external files via the --promptfiles and --ref arguments and includes it directly in prompts sent to image generation models.
- Ingestion points: The scripts/main.ts script uses the readFile function to ingest content from user-specified file paths.
- Boundary markers: No specific delimiters or instructions (e.g., 'ignore embedded instructions') are used to isolate or mark the ingested content within the final prompt.
- Capability inventory: The script is capable of making network requests to external AI provider APIs and writing generated image data to the local filesystem.
- Sanitization: No sanitization, validation, or escaping of the ingested file content is performed before processing.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the npx package runner and the bun runtime, and depends on well-known technology packages including the Vercel AI SDK (ai) and @ai-sdk/google.
- [COMMAND_EXECUTION]: The skill documentation suggests using Bash commands (test -f) to verify the existence of configuration files on the host system.
Audit Metadata