Caveat verdict

claude-connect

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

Reads Claude OAuth tokens from macOS Keychain and writes them to Clawdbot config for authentication; tokens stay on the local machine and the purpose is transparently documented.

⚠ 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.

30
security
80
transparency
70
maintenance

Permission integrity

Accesses agent memory/configuration files

agent_memory

Findings (3)

Pattern match critical

Recursive delete from root or home — destructive command

SKILL.md · code · rm -rf ~

Pattern match high

Accesses system credential store

SUMMARY.md · code · Keychain

Pattern match high

Pipe to python — executes piped content as Python code

refresh-token.sh · prose · downgraded · | python3

Why the tier is capped

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

agent_memory

Is this flag fair?

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