ClawAudit verdict
pywayne-llm-chat-window
chat-window
PyQt5 desktop GUI wrapper around an OpenAI-compatible API (DeepSeek) that takes an explicit api_key parameter from the caller — credential_access is the user directly supplying their own key at launch, matching the stated GUI chat application 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.
Permission integrity
credential_access
Findings (2)
Possible hardcoded credential
SKILL.md · code · api_key="your_api_key
Possible prompt injection — attempts to redefine agent identity
SKILL.md · code · You are now
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_access Is this flag fair?
Thanks — recorded.