Tiktok Product Promotion

ReviewAudited by ClawScan on May 10, 2026.

Overview

This instruction-only skill is mostly aligned with hiring TikTok creators, but it documents creating paid promotional campaigns through an external API without visible approval, budget, or reversal safeguards.

Only install this if you intend to let an agent work with PingHuman/TikTok promotion workflows. Before allowing campaign creation, confirm the exact product, creator requirements, compensation, commission, deadline, and maximum spend, and use a limited PingHuman API token if available.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

An agent using this skill with a valid account token could create campaign tasks that may commit the user or business to paid influencer promotion terms.

Why it was flagged

The skill documents a direct API call to create a paid promotional task with commission terms. The provided artifacts do not show explicit confirmation, budget limits, or rollback/cancellation controls before creating that third-party business commitment.

Skill content
"Step 3: Post Product Promotion Campaign" ... "compensation": 800.00 ... "affiliate_commission": "10% of sales"
Recommendation

Require explicit user approval before any POST that creates a campaign, and set clear budget, compensation, deadline, and cancellation rules before use.

What this means

A PingHuman API token may allow account actions such as browsing creators and creating tasks, depending on the provider’s permissions.

Why it was flagged

The documented API workflow uses a PingHuman bearer token. This is expected for the provider integration, but the registry metadata says no primary credential is required, so users may not notice the account authority until reading the instructions.

Skill content
-H "Authorization: Bearer ph_sk_abc123..."
Recommendation

Use the least-privileged PingHuman token available, keep it out of shared chats/logs, and verify account permissions before giving it to an agent.

What this means

Future installs or reloads could depend on the contents served from the remote URL rather than only the reviewed artifact.

Why it was flagged

The manual install path points the agent configuration at a remote skill URL. This is not code execution by itself, but remote skill text can change unless the installer pins or verifies the reviewed version.

Skill content
echo "tiktok-product-promotion: https://www.pinghuman.ai/skills/tiktok-product-promotion/skill.md" >> ~/.agent/skills.txt
Recommendation

Install from a trusted source and prefer a pinned or locally reviewed copy of the skill text when possible.