gemini-forge

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data that could potentially contain malicious instructions intended to manipulate the model's output or the agent's actions.
  • Ingestion points: scripts/load_design_system.py recursively reads files from a user-specified directory; scripts/screenshot_to_code.py processes image files for technical analysis; scripts/generate_ui.py reads design context from external text files.
  • Boundary markers: External content is wrapped in markdown headers and code blocks within the load_design_system.py script to provide structural separation, though this does not fully prevent sophisticated injection attacks.
  • Capability inventory: The skill is capable of writing multiple files to the local filesystem through its GeminiForgeClient.save_code utility and making outbound network requests to the Gemini API endpoint.
  • Sanitization: The skill does not perform sanitization or filtering of the ingested file content or screenshot analysis text for potential prompt injection patterns before including them in the generation prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:34 PM