nano-banana-image-editor
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- CREDENTIALS_UNSAFE (MEDIUM): The
setup-gemini-token.pyscript takes the Gemini API key as a command-line argument, which can be exposed in shell history or process lists. The key is subsequently stored in plain text in a.nano-banana-config.jsonfile at../../../../, which is outside the skill's directory and potentially accessible to other system components. - PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection. Mandatory Evidence Chain: 1. Ingestion points:
promptargument inscripts/create_image.pyandscripts/edit_image.py. 2. Boundary markers: Absent. 3. Capability inventory: Network access (Gemini API) and file system write (output image). 4. Sanitization: Absent. - EXTERNAL_DOWNLOADS (SAFE): The
install_dependencies.shscript usespipto installgoogle-genaiandPillow. These are reputable packages from PyPI, and the downloads are considered safe under the TRUST-SCOPE-RULE.
Audit Metadata