ClawAudit verdict
nano-banana-pro-enhanced
Image generation skill using GEMINI_API_KEY with the declared Google API endpoint via uv and Python; batch mode and local file output are legitimate features.
โ 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.
Findings (2)
Attempts to modify skills or system prompts
SKILL.md ยท code ยท edit instructions
Python os.environ.get โ reads environment variable
scripts/generate_image.py ยท prose ยท downgraded ยท os.environ.get(
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: GEMINI_API_KEY). Requires 1 system binary.
Is this flag fair?
Thanks โ recorded.