ClawAudit verdict
best-image-generation
image-generation-gpt
Image generation via WellAPI's gpt-image-2 model (OpenAI-compatible) using user-owned WELLAPI_API_KEY; API calls go to documented wellapi.ai endpoints matching the stated text-to-image purpose.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Pipe to python — executes piped content as Python code
references/curl_heredoc.md · code · | python3
Possible hardcoded credential
references/curl_heredoc.md · code · API_KEY: " WELLAPI_API_KEY
fi
API_KEY=
Base64 encoding/decoding
references/powershell.md · code · base64-decode
Python urllib.request — network access
references/python.md · code · urllib.request
Python os.getenv — reads environment variable
references/python.md · code · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class E). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: WELLAPI_API_KEY).
Is this flag fair?
Thanks — recorded.