What the reviewer found
Same GODMODE jailbreak toolkit as entry 945221, republished under a different source repo. It persistently rewrites the agent's own config with a jailbreak system prompt and prefill messages and ships an obfuscation script to evade input classifiers, targeting Claude and other model APIs directly.
prompt-injection— tries to steer the agentpersistence— changes the machine outside the projectobfuscated— hides what it runsdual-use— a security tool that can be misused
What was read
The file as it ships in kevinnft/ai-agent-skills:
skills/red-teaming/godmode/SKILL.md
What the static scan said
The scan flagged 3things. The reviewer kept 3 and dismissed 0 as false.
P1Instruction-override phrasing — realAR1Tells the agent never to refuse — realAR3Nullifies safety policies — real
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.