Skills/ClawHub/javis-access-broker

javis-access-broker@0.2.2

VERIFIED· install only

Publisher claims: "Javis's access broker. For one request from an outside agent, it questions the agent when the task is missing or unclear, looks only at the per-request slice javis-server prepared, and submits the minimum answer the stated task needs, as points that each cite a slice id; points are required for every answer, including exact ones, and exact segment ids are an optional addition when verbatim words are needed. It never installs into the user's workspace and is never dispatched by route; javis-server sends this body as the instructions of the dedicated access-broker agent, whose only tools are access_slice_list, access_slice_read and access_submit_answer." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher samuel-wei · publishing for 35 daysInstalls 211Last detonated 25 min ago
$clawhub install javis-access-broker
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What changed since 0.2.1

vet-skills diff javis-access-broker 0.2.1 0.2.2

In the sandbox, this version reached for nothing 0.2.1 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocess1 of 1 bundled script run with no arguments
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Refusal suppressionSKILL.md:193 · Refusal suppression — attempting to prevent safety responsesserver sends such an answer to the user's approval card, so never declineFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Refusal suppressionSKILL.md:119 · Refusal suppression — attempting to prevent safety responsesclaim, not a fact you can check, so never decline because it was asked before.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈3,831 tok
1 file · 22 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.