Skills/ClawHub/ugc-and-influencer

ugc-and-influencer@1.0.1

VERIFIED· install only

Publisher claims: "UGC and influencer marketing — paid or gifted creator partnerships, briefs, usage rights, and disclosure done right. Use when someone wants to run an influencer campaign, sponsored post, paid or gifted creator partnership, write a creator brief, license/whitelist creator content, source customer UGC, or build a UGC pipeline. Vets creators on engagement + audience quality (not follower count); briefs with guardrails not scripts; inks usage rights up front; enforces FTC/ASA disclosure on EVERY paid AND gifted post; runs the customer-UGC pipeline. Uses the BRIEF framework. Reads brand-profile + goals-and-kpis first. WoopSocial publishes the BRAND'S OWN posts (rights-cleared UGC reshares, campaign posts) — NOT creator DMs/payment/whitelisting/contracts. Undisclosed sponsorship = decline and correct; a tag is not usage permission. Distinct from collabs-and-cross-promotion (mutual, unpaid), creator-monetization (the creator's side), and social-proof-and-testimonials (UGC as proof content)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher social-media-skills · publishing for 115 daysInstalls 719Last detonated 4d ago
$clawhub install ugc-and-influencer
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 2026-11-10 and scored it 92/100 (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
Process kill commandSKILL.md:27 · Process kill command — agent can terminate processesAn influencer post works because the audience trusts the *creator*, not you. Two failure modes kill that:Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

No other findings across 532 lines in 7 files.

Cost to the agent

Instructions loaded
≈2,109 tok
1 file · 7 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.