ClawAudit verdict
claw-mail
This is a multi-account IMAP/SMTP email management skill with explicit TLS enforcement, hardened ciphers, and support for 1Password/Keychain credential storage; the credential_store capability is used transparently for secure email account credentials.
⚠ 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 (10)
Possible hardcoded credential
SKILL.md · code · password: "op://Work/IMAP/password
Accesses system credential store
SKILL.md · frontmatter · Keychain
Pipe to python — executes piped content as Python code
scripts/compose_mail.py · prose · downgraded · | python3
<script> tag in markdown — potential code injection
scripts/lib/composer.py · prose · downgraded · <script>
References webhook/callback URL
references/REFERENCE.md · code · webhook_url
subprocess execution — runs system commands from Python
scripts/lib/credential_store.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/lib/credential_store.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/lib/oauth2.py · prose · downgraded · urllib.request
Base64 encoding/decoding
scripts/lib/oauth2.py · prose · downgraded · base64-encode
Popular HTTP library — network access
scripts/reply_mail.py · prose · downgraded · Got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
credential_store Is this flag fair?
Thanks — recorded.