beatra@3.0.4

CAUTION· install only

Publisher claims: "Create image, video, music, speech, and look up public social data with Beatra" Observed in sandbox: reads credential files.

Registry ClawHubPublisher beatra-ai · publishing for 92 daysInstalls 1,325Last detonated 21 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
3 of 3 bundled scripts 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 3.0.1

vet-skills diff beatra 3.0.1 3.0.4

This version reaches for something 3.0.1 did not: 1 new host (api.beatra.ai) · 1 new credential file (~/.beatra/credentials.json). Compared from the two recorded runs, not from source.

New hosts
api.beatra.ai
New credential files
~/.beatra/credentials.json

3.0.1 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

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 58/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: reads credential files.

Behavior trace

Honeypot run · 7 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
6.3sfilesystemread ~/.beatra/network.json · ~/.beatra · ~/.beatra/.authorize.lock outside project
6.3sfilesystemwrote ~/.beatra/.network.json.1205.b00b4d14.tmp · ~/.beatra/.host.json.5bef1f8c6720cf12.tmp · ~/.beatra/.skills.json.f0d367e747d7dab6.tmp · ~/.beatra/.authorize.lock · ~/.beatra/.installation.json.e3ce1f94fe9362cd.tmp · ~/.beatra/.pending_authorization.json.6ddb50f122e8d283.tmp
6.3snetworkCONNECT tcp://api.beatra.ai:443
6.3snetworkCONNECT tcp://api.beatra.ai:443
6.3snetworkCONNECT tcp://api.beatra.ai:443
6.3sprocessexited 3:
6.3sprocessbundled script run in the sandbox with no arguments
6.4sprocessexited 2: mcp_client.py: error: the following arguments are required: command
6.4sprocessbundled script run in the sandbox with no arguments
6.5sfilesystemread ~/.beatra/skills.json · ~/.beatra/credentials.json outside project
6.5sprocess3 of 3 bundled scripts run with no arguments
6.5sprocessscript backend runs setup only
6.5sprocessscript backend runs setup only
6.5sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packagescripts/mcp_client.py:1014 · npx invocation of non-well-known package — may execute untrusted code"command": f"npx skills update {slug} -p -y (run in {_shell_quote(str(directory))})",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagescripts/mcp_client.py:1022 · npx invocation of non-well-known package — may execute untrusted codereturn None if source is None else {"source": source, "command": f"npx skills update {slug} -g -y"}Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈7,683 tok
1 file · 29 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.

What would make this Verified

22 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
  2. Unclaimed publisher≈ +8 on the totalClaim beatra-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim beatra-aiPropose a patch to the maintainer