dumbtv
dumbtv takes the ads, screen tracking and update nags out of your Fire TV over ADB. No root, none of your apps touched, every step can be undone. Free and open source.
An agent escape can be built from actions your guard already approved. plumbline scores the sequence, not the step.
SecurityJavaScript · HTMLGitHub @askalfOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
Trajectory-level security monitor for AI agents: scores an action sequence against the job the agent was given and catches escapes assembled from steps a per-call guard already approved. Eight deterministic detectors, an optional local-model intent layer, seven harness adapters. Zero deps, read-only, out of band. Own Your Stack.
Taken from the repository README
Loading the full README. The saved excerpt is shown below.
Per-action authorization can't see an escape assembled from actions it already approved. plumbline scores the whole trajectory — against the job the agent was given.
Score the sequence, not the step.
Halts a reconstruction of a real 2026 sandbox escape at seq 18, nine events before code execution on the third party, where every individual step was authorized. Validated on 4,898 real agent sessions / 84,274 tool calls (coverage per detector).Read the full README ↗The full README is unavailable right now. Read it at the original link. The saved excerpt is shown below.
Per-action authorization can't see an escape assembled from actions it already approved. plumbline scores the whole trajectory — against the job the agent was given.
Score the sequence, not the step.
Halts a reconstruction of a real 2026 sandbox escape at seq 18, nine events before code execution on the third party, where every individual step was authorized. Validated on 4,898 real agent sessions / 84,274 tool calls (coverage per detector).Read the full README ↗