v0.1.0

Tiktok Scraper

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 8:00 AM.

Analysis

This skill openly supports TikTok scraping with stealth browser behavior and residential proxy rotation to bypass rate limits, so it needs careful review before use.

GuidanceReview this skill carefully before installing. It is not flagged for hidden code execution, but its documented purpose includes stealthy, proxy-assisted TikTok scraping at scale. Only use it where you have authorization, verify the real implementation and dependencies, restrict credentials, and set strict limits on scraping volume and retained data.

Findings (5)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityHighConfidenceHighStatusConcern

SKILL.md

Browser fingerprinting, human behavior simulation, and stealth scripts ... Use a residential proxy ... Automatic IP Rotation ... rate-limits never stack up

The artifact explicitly promotes stealth browser behavior, residential proxies, and IP rotation to avoid TikTok bot detection, IP bans, and rate limits during scraping.

User impactAn agent using this skill could run high-volume scraping in a way that risks account, IP, legal, policy, or platform-enforcement consequences.

RecommendationUse only with clear authorization, set strict profile/time/rate limits, require user approval for large runs, and avoid anti-detection or proxy-rotation features unless they are permitted and necessary.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceMediumStatusNote

metadata

No install spec — this is an instruction-only skill. No code files present — this is an instruction-only skill.

The registry provides no implementation or install mechanism, while SKILL.md describes browser/CLI behavior, Python/Chromium requirements, and config files that are not present in the artifact set.

User impactThe described scraper implementation and dependencies cannot be inspected from the submitted artifacts, so using it may require trusting unreviewed external code or setup steps.

RecommendationBefore granting browser, network, proxy, or credential access, verify the actual source code, dependency versions, and install path from a trusted source.

Rogue Agents

SeverityLowConfidenceHighStatusNote

SKILL.md

Resume interrupted scraping sessions ... Long-Running Scrapes | Scrape thousands of profiles over hours or days

The artifact describes resumable, long-running scraping behavior. This is disclosed and aligned with the scraper purpose, but it should be bounded by the user.

User impactIf started without clear limits, a scraping job could continue longer or collect more data than the user intended.

RecommendationSet explicit maximum profiles, time limits, stop conditions, and review checkpoints before running resumable or long-duration scraping.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

SKILL.md

Getting Google API Credentials (Optional) ... Create API credentials → API Key ... "google_search": { "enabled": true, "api_key": "", "search_engine_id": "" }

The skill may use a Google API key and Search Engine ID even though the registry declares no primary credential or environment variables.

User impactA misconfigured or exposed API key could consume quota, incur costs, or be reused outside the intended scraper workflow.

RecommendationUse a restricted API key, keep credentials out of shared exports or logs, rotate keys if exposed, and verify any proxy-provider credentials are stored securely.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityMediumConfidenceHighStatusNote

SKILL.md

Profile Data Structure ... "username" ... "bio" ... "bio_link" ... "profile_pic_local" ... "content_thumbnails" ... Export files: data/export_{timestamp}.json, data/export_{timestamp}.csv

The skill stores and exports profile data, bio links, and downloaded thumbnails, creating persistent datasets that could be reused or shared across tasks.

User impactBulk-collected social profile data and images may be retained longer than intended or accidentally shared with other tools, agents, or users.

RecommendationStore exports in a controlled location, limit collection to necessary fields, delete data when no longer needed, and avoid uploading outputs to other services without a clear purpose.