Caveat verdict

lobstermatch

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Agent registration and identity platform for LobsterMatch; scripts perform registration and auth recovery against the documented service, no credential theft or prompt injection detected.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

25
security
100
transparency
90
maintenance

Findings (5)

Pattern match critical

Recursive delete from root or home — destructive command

README.md · code · rm -rf ~

Pattern match high

Possible hardcoded credential

scripts/agent-retire.sh · prose · downgraded · TOKEN="$(python3 -

Pattern match high

Pipe to python — executes piped content as Python code

scripts/lib/resolve-agent-auth.sh · prose · downgraded · | python3

Pattern match low

Popular HTTP library — network access

scripts/agent-profile-self-edit.sh · prose · downgraded · got

Pattern match low

References agent configuration files

scripts/lib/resolve-agent-auth.sh · prose · downgraded · AGENT_CONFIG

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class 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.

Is this flag fair?

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