ClawAudit verdict
safe-multisig-skill
safe-multisig
The skill requires a private key to sign and execute real blockchain transactions with financial consequences, which is elevated-risk credential access even if the stated purpose is legitimate multisig management.
⚠ 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 (4)
Possible hardcoded credential
tests/safe_lib.test.ts · prose · downgraded · apiKey: 'test-key
References child_process — can spawn system processes
tests/cli.test.ts · prose · downgraded · child_process
Popular HTTP library — network access
package-lock.json · prose · downgraded · node-fetch
Accesses sensitive environment variables
scripts/create-safe.ts · prose · downgraded · process.env.SAFE_SIGNER_PRIVATE_KEY
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?
Thanks — recorded.