ClawAudit verdict

lobstermail

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

AI agent email skill creating @lobstermail.ai inboxes via the declared API; auto-signup stores credentials locally (~/.lobstermail/token), all network operations target only the declared api.lobstermail.ai endpoint.

⚠ 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.

20
security
80
transparency
90
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (2)

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

README.md · code · curl -sL https://api.lobstermail.ai/install | sh

Pattern match critical

Pipe to sh — executes piped content as shell commands

README.md · code · | sh

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B). 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.

network_outnetwork_inpackage_install

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API