ClawAudit verdict
AI Email Agent
ai-email-agent
An LLM-powered email auto-reply system that processes emails via IMAP/SMTP using user-provided credentials and an LLM API key; all capabilities (classification, sentiment, auto-reply) match the stated e-commerce customer service purpose with no evidence of data exfiltration or malicious behavior.
⚠ 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
package_install
Findings (3)
Possible hardcoded credential
SKILL.md · code · API_KEY="sk-your-key
Python os.environ.get — reads environment variable
agent/config_loader.py · prose · downgraded · os.environ.get(
References webhook/callback URL
config.yaml · prose · downgraded · WEBHOOK_URL
Permissions & capabilities
Requires 3 environment variables. (3 sensitive: LLM_API_KEY, IMAP_PASSWORD, SMTP_PASSWORD). Requires 1 system binary.
package_install Is this flag fair?
Thanks — recorded.