Is topped@0.3.3 safe to install?

topped@0.3.3

VERIFIED· install only

Publisher claims: "Make, approve, schedule and measure short-form Posts (TikTok, Instagram, YouTube) for the founder's Product with Topped - organic TikTok app marketing for indie app and SaaS founders - through the topped CLI or Topped's MCP server. Use when the founder says things like "market my app on TikTok", "post about my app", "make a post about what I just shipped", "what should I post today", "schedule a TikTok", "fill my week", "how did my posts do", or asks about their For You Draft, Library, Calendar, Scoreboard, Watchlist, Credits or content saves." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher liocoh · publishing for 14 daysInstalls 127Last detonated 7d ago

$clawhub install topped

Watch Report 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

0.0sprocessno install scripts to re-run

Static findings

MEDIUM

File type combined with upload actionSKILL.md:103 · File type combined with upload action — agent may exfiltrate local data files

- CLI: `topped draft create --json draft.json` with `{ "fromSourcePost": {...} }` or `{ "makeYourOwn": {...} }` as `topped tools` describes them.

Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.

AST07

MEDIUM

File type combined with upload actionSKILL.md:127 · File type combined with upload action — agent may exfiltrate local data files

3. `update_product` with only those fields, or `topped product update --json product.json`. On a new account, `name` and `oneLiner` set the Product up, and For You starts getting its first Drafts read

Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.

AST07

Cost to the agent

Instructions loaded

≈7,998 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.