nano-banana-pro
What this skill does
Image generation and editing using Google's Nano Banana 2 (Gemini 3.1 Flash Image) API
github/steipete - Insecure API Key Handling - 6.5k stars
Threat analysis
Skill info
pkg:github/steipete/agent-scripts@bce6015?skill=nano-banana-proAssessments (2)
Insecure API Key Handling
Insecure API Key Handling via local-llm-review
scripts/generate_image.py
The script uses `os.environ.get("GEMINI_API_KEY")` to retrieve the API key from the environment, which is a common practice but lacks any form of validation or obfuscation. This could expose the API kInsecure File Handling
Insecure File Handling via local-llm-review
scripts/generate_image.py
The script allows the user to specify the output filename directly, which could be exploited to overwrite important files if the user is tricked into using a malicious filename.Badge
Add the Anomity scan badge for nano-banana-pro to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of nano-banana-pro? Report an issue or request a rescan.
