Skills/ClawHub/narrator

narrator@1.3.2

VERIFIED· install only

Publisher claims: "Live narration of your macOS screen activity with Gemini vision + ElevenLabs speech." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher buddyh · publishing for 278 daysInstalls 1,917Last detonated 37 min ago
$clawhub install narrator
WatchReport an issue

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

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 2026-11-22 and scored it 89/100 (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 · 15 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocessexited 1: [narrator] Canonical repo not found: /Users/buddy/narrator
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15sprocessexited 1: [narrator] Canonical repo not found: /Users/buddy/narrator
15sprocess3 of 3 bundled scripts run with no arguments
15sprocessscript backend runs setup only
15sprocessscript backend runs setup only
15sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedserver.py:46 · Python subprocess execution detectedproc = subprocess.run(cmd, cwd=str(repo_dir), env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmain.py:45 · Python subprocess execution detectedproc = subprocess.run(cmd, cwd=str(repo_dir), env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandhorror_demo.py:32 · File permission modification command — agent changes file ownership/permissions"chmod 777... they've doomed us all!",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈553 tok
1 file · 4 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.