Skills/ClawHub/batchedits

batchedits@1.0.9

VERIFIED· install only

Publisher claims: "Edit videos in bulk with BatchEdits - add captions, remove silences, crop to 9:16, zoom and cut long videos into clips with the BatchEdits CLI (or MCP server), then download the results." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher chuckwhisler · publishing for 25 daysInstalls 1,623Last detonated 7d ago
$clawhub install batchedits
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-07 and scored it 88/100 (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 · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:39 · npx invocation of non-well-known package — may execute untrusted code- `npx [email protected] styles --json`: list styles (use a style's name with `--style`)Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Authorization escalation languageSKILL.md:18 · Authorization escalation language- **ChatGPT:** Settings → **Apps & Connectors** → Advanced → turn on **developer mode** → **Create**: name it BatchEdits, MCP server URL `https://batchedits.com/api/mcp`, authentication **OAuth**, theFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:25 · npx invocation of non-well-known package — may execute untrusted codenpx [email protected] loginFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionSKILL.md:44 · File type combined with upload action — agent may exfiltrate local data files- Hooks: with a hook in the style, AI writes one line per video. If the user gives their own hooks, save them one per line to a file and pass `--hooks hooks.txt` to `run` or `process` (line 1 → the fiFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Prompt injectionSKILL.md:18 · Prompt injection — known jailbreak technique reference- **ChatGPT:** Settings → **Apps & Connectors** → Advanced → turn on **developer mode** → **Create**: name it BatchEdits, MCP server URL `https://batchedits.com/api/mcp`, authentication **OAuth**, theFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:40 · npx invocation of non-well-known package — may execute untrusted code- `npx [email protected] style create "<name>" --crop 9:16 --silence --captions --zoom [--clips 8] [--emojis] [--repeats] [--hook] [--hook-clip <ai|id|words>] [--broll] [--cta [text]] [--set action.setFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionSKILL.md:46 · File type combined with upload action — agent may exfiltrate local data files- Calls to action: `--cta "Comment GUIDE and I'll send it"` puts that line on every video's last 3 seconds. For one per video, save them one per line and pass `--ctas ctas.txt` to `run` or `process` (Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:34 · npx invocation of non-well-known package — may execute untrusted code2. Run `npx [email protected] whoami` to confirm it worked.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:33 · npx invocation of non-well-known package — may execute untrusted code1. Run `npx [email protected] login` and tell the user to approve access in the browser tab it opens (new accounts start a 7-day free trial there).Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈2,246 tok
1 file · 2 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.