ClawAudit verdict
sendgrid
sendgrid-skills
The skill provides guidelines for using an email platform, with no evidence of 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.
Findings (5)
Dynamic import() — loads module at runtime
send-email/references/installation.md · code · import (
"
Accesses sensitive environment variables
README.md · code · process.env.SENDGRID_API_KEY
Python os.environ.get — reads environment variable
send-email/references/installation.md · code · os.environ.get(
References webhook/callback URL
scripts/verify-inbound-setup.sh · prose · downgraded · WEBHOOK_URL
Base64 encoding/decoding
send-email/SKILL.md · prose · downgraded · Base64-encode
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: SENDGRID_API_KEY). Requires 3 system binaries. (1 elevated: curl).
Is this flag fair?
Thanks — recorded.