Icp Qualifier

PassAudited by VirusTotal on May 12, 2026.

Overview

Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill The skill bundle is designed for ICP qualification, instructing the AI agent to research public information (websites, Instagram) to score leads. The `SKILL.md` provides clear, task-specific instructions for information gathering and output formatting, without any evidence of prompt injection attempts to subvert the agent's purpose, access unrelated sensitive data, or execute unauthorized commands. No malicious code, data exfiltration, persistence mechanisms, or obfuscation were found across any files (`_meta.json`, `SKILL.md`, `package.json`, `skill.yaml`). The `skill.yaml` explicitly declares `tools: []`, indicating no external tools are requested.

Findings (0)

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

The agent may include founder names, emails, and public or social-media observations in its lead qualification output.

Why it was flagged

The workflow asks the agent to retrieve external web/social content and contact details for leads. This is directly related to lead qualification and the artifacts show no storage or onward transmission, but personal/business contact data and untrusted retrieved context may enter the conversation.

Skill content
"Review Instagram" ... "Find contact info — Founder name, email if available"
Recommendation

Use only lawful/public business information, treat web and social content as data rather than instructions, and avoid retaining or reusing contact details beyond the intended outreach workflow.