Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Outbound Campaign Auto
v1.0.0Automates full outbound campaigns by scraping qualified leads, segmenting them, creating personalized email and LinkedIn sequences, ad hooks, video assets, a...
⭐ 0· 42·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md describes heavy integration with Apify (multiple scrapers), InVideo AI, and Claude AI and explicitly shows example inputs containing apify_token and invideo_api_key. However, the registry metadata lists no required environment variables or primary credential. That is inconsistent: a lead-scraping + video-generation skill legitimately needs API credentials for those services, so the metadata omission is unexplained and disproportionate.
Instruction Scope
The runtime instructions instruct the agent to perform web scraping (LinkedIn companies and profiles, website crawling, Google News), find/verify emails, gather personal context from posts, and send data to InVideo for video generation and to Claude for copywriting. Those actions are aligned with the described purpose, but they involve collecting personal data (emails, LinkedIn profile contents) and external network calls. The SKILL.md does not specify where outputs or scraped data are stored or whether data is transmitted to any endpoints beyond the named services; it also contains affiliate links but no explicit data-flow or consent/retention guidance.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so there is no automatic binary download or archive extraction risk. That limits disk‑write/exec risk from the skill package itself.
Credentials
The SKILL.md example input explicitly includes 'apify_token' and 'invideo_api_key' (and references Claude). Yet the skill metadata declares zero required environment variables and no primary credential. Requiring API tokens for scraping and video generation is expected; not declaring them is an incoherence that obscures what secrets the skill will ask for at runtime. The skill will handle PII (emails, names, LinkedIn URLs), so any credentials supplied should be minimal-scope and ephemeral — this is not documented.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request persistent presence or modify other skills. Autonomous invocation is allowed by default (disable-model-invocation is false) — combined with the scraping/data-collection behavior this increases blast radius, but the skill itself does not request elevated platform privileges or 'always' persistence.
What to consider before installing
This skill's instructions make sense for an outbound-campaign tool, but the package metadata fails to declare the API credentials it clearly needs (Apify, InVideo, Claude). Before installing or running it: (1) ask the publisher to explicitly list required credentials and exactly how/where data is sent and stored; (2) never provide high‑privilege or long‑lived credentials — use scoped, revocable API keys or per-run tokens; (3) confirm compliance with LinkedIn and data‑protection terms before scraping personal profiles and collecting emails; (4) test in a sandbox account and inspect the outputs for PII exposure; and (5) prefer a skill that documents data retention, error handling, and where scraped data is uploaded. If the publisher cannot clarify these points, avoid using it with real credentials or sensitive data.Like a lobster shell, security has layers — review code before you run it.
latestvk974y6z1bd0q74gakhrhz397mn84kz35
License
MIT-0
Free to use, modify, and redistribute. No attribution required.