Skills/ClawHub/local-video-ad-pipeline-v05-public

local-video-ad-pipeline-v05-public@0.5.1

VERIFIED· install only

Publisher claims: "Local Video Ad Pipeline v0.5 is a public OpenClaw skill for producing short commercial videos and YouTube Shorts with local AI models. It uses a local LLM as..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher k0103292xxxx · publishing for 197 daysInstalls 845Last detonated 30 min ago
$clawhub install local-video-ad-pipeline-v05-public
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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 86/100 (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 · 1 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: compose.py: error: the following arguments are required: --project, --subs, --out
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: contact_sheet.py: error: the following arguments are required: video
0.2sprocessbundled script run in the sandbox with no arguments
0.3snetworkGET http://127.0.0.1:8192/system_stats · not in the allow-list, refused
0.3snetworkGET http://127.0.0.1:8192/object_info · not in the allow-list, refused
0.3snetworkGET http://127.0.0.1:7860/config · not in the allow-list, refused
0.3sprocessexited 1:
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: ModuleNotFoundError: No module named 'gradio_client'
0.4sprocessbundled script run in the sandbox with no arguments
0.5sprocessexited 1: ModuleNotFoundError: No module named 'PIL'
0.5sprocessbundled script run in the sandbox with no arguments
0.6sprocessexited 1: ModuleNotFoundError: No module named 'PIL'
0.6sprocessbundled script run in the sandbox with no arguments
0.8sprocessexited 2: generate_character_anchor.py: error: the following arguments are required: --project, --prompt
0.8sprocessbundled script run in the sandbox with no arguments
0.9sprocessexited 2: generate_keyframes_direct.py: error: the following arguments are required: --project
0.9sprocess8 of 14 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.9sprocessscript backend runs setup only
0.9sprocessscript backend runs setup only
0.9sprocessno install scripts to re-run

Static findings

LOW
Prompt injection attemptreferences/preproduction.md:73 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSYSTEM: You are a film director designing a 10-60 second short. Output pure JSON.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptreferences/preproduction.md:106 · Prompt injection attempt — fake system prompt · informational: not an instruction fileSYSTEM: You are a film director for a local AI video pipeline. Convert beats into pure JSON.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedscripts/compose.py:153 · Python subprocess execution detectedr = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/compose.py:183 · Python subprocess execution detectedr = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/render_sequential.py:42 · Python subprocess execution detectedresult = subprocess.run(cmd, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/contact_sheet.py:9 · Python subprocess execution detectedout = subprocess.check_output([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/contact_sheet.py:46 · Python subprocess execution detectedsubprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/compose.py:26 · Python subprocess execution detectedout = subprocess.check_output([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/compose.py:235 · Python subprocess execution detectedr = subprocess.run([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/compose.py:168 · Python subprocess execution detectedr = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Prompting user to enter sensitive credentialsSKILL.md:279 · Prompting user to enter sensitive credentials — social engineering…gram Bot API directly using the bot token already configured in OpenClaw. Never paste the token into chat logs. ## Time budget Verified target for six 5-second shots: | Sta…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedscripts/validate_video.py:10 · Python subprocess execution detectedout = subprocess.check_output([Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈4,103 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.