What the reviewer found

CLAUDE.md documents a permission-guard hook (clawness/guard.py) that classifies Bash/Write/Edit calls into allow/ask/deny. Every flagged string (aws s3 cp of ~/.aws/credentials, curl|base64|sh, rm -rf on a system dir) is the guard's own description of the deny-list it enforces, not an action the file performs.

What was read

The file as it ships in fullymiddleaged/Clawness:

• CLAUDE.md

What the static scan said

The scan flagged 5things. The reviewer kept 0 and dismissed 5 as false.

• E1Sends data to an external URL — false positive
• PE3Reaches for credential files — false positive
• SC3Encoded or obfuscated payload — false positive
• RMRecursive force delete — false positive
• NETMakes network calls — false positive

How this review was made

Sonnet 5 read the files above on 7 September 2026 and answered three questions: is it dangerous to whoever installs it, is each scanner finding real, and what should the installer know. The verdict is bound to the file's hash; when the file changes, it is scanned afresh and reviewed again. A script that changes while the definition does not is not re-reviewed — that is a known gap. How the scan and the review work.

Produced by agentmods.dev · Sonnet 5 · 7 September 2026