PhantomBuster

Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.

Security Scan

The skill's code and README match its stated purpose (controlling PhantomBuster via API), but the registry metadata omits the required API credential and the package has no verifiable source/homepage — this mismatch reduces trust.

Purpose & Capability

The name, description, SKILL.md, and pb.py all consistently implement PhantomBuster API operations (list, launch, status, abort, fetch results). However, the registry metadata claims no required environment variables or primary credential even though both SKILL.md and pb.py require PHANTOMBUSTER_API_KEY. Also the skill has an unknown source and no homepage, which reduces provenance.

Instruction Scope

Runtime instructions are narrowly scoped: read PHANTOMBUSTER_API_KEY from the environment, call PhantomBuster API endpoints, and download result.csv from phantombuster.s3.amazonaws.com. The SKILL.md explicitly instructs the user to set PHANTOMBUSTER_API_KEY. There are no instructions to read unrelated files, other env vars, or to exfiltrate data to unexpected endpoints.

Install Mechanism

There is no install spec (instruction-only skill) and included code is a small, plain Python CLI. Nothing is downloaded or extracted during install, so no high-risk install behavior is present.

Credentials

The skill requires a sensitive secret (PHANTOMBUSTER_API_KEY) as shown in SKILL.md and pb.py, but the registry metadata does not declare any required env vars or primary credential — an inconsistency that can mislead users about what secrets they must provide. Aside from that, the only environment access in code is this single API key, which is proportional to the stated purpose.

Persistence & Privilege

The skill is not always-enabled and does not request persistent system privileges or modify other skills' configs. Autonomous invocation is allowed (platform default) but not combined with other high-risk factors here.

What to consider before installing

What to consider before installing: - This skill does what it says: it uses your PhantomBuster API key to list/launch/abort agents and download results. The pb.py code is short and readable and shows the environment variable PHANTOMBUSTER_API_KEY is required. - The registry metadata failing to declare the required API key and primary credential is a red flag — the metadata should advertise that it needs PHANTOMBUSTER_API_KEY. Ask the publisher to correct the metadata before trusting the skill. - There is no homepage or known source/maintainer; prefer skills with a verifiable source. If you proceed, only provide an API key with the minimum necessary privileges (if PhantomBuster supports scoped or limited keys), and consider using a throwaway or rate-limited account if possible. - The skill will download result.csv from phantombuster.s3.amazonaws.com using paths returned by the API — verify this behavior against your expectations and that result data may include scraped personal data (ensure legal/compliance considerations). - If you need higher assurance, run the included pb.py in a sandboxed environment or inspect/modify it yourself; request the maintainer to update registry metadata to explicitly list PHANTOMBUSTER_API_KEY as required and add a homepage/source link. - Confidence in this assessment is medium because the code is straightforward and coherent with the description, but provenance and metadata mismatches lower trust.

PhantomBuster Skill

Control your PhantomBuster automation agents from the command line.

Setup

1. Get your API key from Workspace Settings
2. Set the environment variable:

   export PHANTOMBUSTER_API_KEY=your-api-key-here
   

Usage

All commands use the bundled pb.py script in this skill's directory.

List Agents

See all your configured PhantomBuster agents.

python3 pb.py list
python3 pb.py list --json  # JSON output

Launch an Agent

Start a phantom by ID or name.

python3 pb.py launch <agent-id>
python3 pb.py launch <agent-id> --argument '{"search": "CEO fintech"}'

Get Agent Output

Fetch the results/output from the most recent run.

python3 pb.py output <agent-id>
python3 pb.py output <agent-id> --json  # Raw JSON

Check Agent Status

See if an agent is running, finished, or errored.

python3 pb.py status <agent-id>

Abort Running Agent

Stop an agent that's currently running.

python3 pb.py abort <agent-id>

Get Agent Details

Full details about a specific agent.

python3 pb.py get <agent-id>

Fetch Result Data

Download the actual result data (CSV) from an agent's latest run.

python3 pb.py fetch-result <agent-id>
python3 pb.py fetch-result <agent-id> > output.csv

This downloads the result.csv file from the agent's S3 storage, perfect for integrating PhantomBuster data into your workflows.

Example Prompts

• "List my PhantomBuster agents"
• "Launch my LinkedIn Sales Navigator scraper"
• "Get the output from agent 12345"
• "Check if my Twitter follower phantom is still running"
• "Abort the currently running agent"

Common Phantoms

PhantomBuster offers many pre-built automations:

• LinkedIn Sales Navigator Search — Extract leads from searches
• LinkedIn Profile Scraper — Get profile data
• Twitter Follower Collector — Scrape followers
• Instagram Profile Scraper — Get IG profile data
• Google Maps Search Export — Extract business listings

Rate Limits

PhantomBuster has execution time limits based on your plan. The API itself is not heavily rate-limited, but agent execution consumes your plan's minutes.