ClawAudit verdict

IMA Nano Banana Image Generator

ai-nano-banana-ima

45
๐ŸŸ  Risky
Significant concerns โ€” only install if you understand the risks

The skill uses the credential_access capability to read the IMA_API_KEY environment variable, which may pose a risk if not properly secured. However, the intent appears to be legitimate image generation.

โš  Flagged for review โ€” coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis โ€” not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

80
security
50
transparency
90
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match low

Popular HTTP library โ€” network access

scripts/ima_image_create.py ยท prose ยท downgraded ยท got

Pattern match low

Python os.getenv โ€” reads environment variable

scripts/ima_image_create.py ยท prose ยท downgraded ยท os.getenv(

Permissions & capabilities

No declared permissions โ€” minimal attack surface.

credential_access

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API