ClawAudit verdict
agentmail
agentmail-temp
The skill appears to be a temporary or test version of the AgentMail skill. It does not contain any malicious code or intent.
⚠ 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
agent_memory
Findings (5)
Possible hardcoded credential
references/WEBHOOKS.md · code · api_key="your_api_key
Python os.getenv — reads environment variable
SKILL.md · code · os.getenv(
References tunneling service
references/WEBHOOKS.md · code · ngrok
Base64 encoding/decoding
references/API.md · code · base64-encode
References webhook/callback URL
scripts/setup_webhook.py · prose · downgraded · webhook.url
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_accessdata_encodingnetwork_inagent_memory Is this flag fair?
Thanks — recorded.