Cold Outreach
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: cold-outreach Version: 2.0.0 The OpenClaw AgentSkills bundle 'cold-outreach' is benign. The `_meta.json` file contains standard metadata. The `SKILL.md` provides extensive instructions, frameworks, and templates for an AI agent to generate cold outreach content (emails, SMS, LinkedIn DMs). All outputs are directed to `workspace/artifacts/`, a sandboxed location. There are no instructions for the agent to perform actions beyond content generation, such as accessing sensitive files, executing arbitrary commands, making external network calls, or engaging in any form of data exfiltration or persistence. The document uses the prompt injection surface solely to guide the agent's content creation process, without any malicious intent or risky capabilities.
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.
Generated messages may be highly persuasive and personalized, so they should be checked for accuracy, consent, and anti-spam compliance before being sent.
The skill is explicitly designed to create persuasive unsolicited outreach using psychological framing. This is disclosed and purpose-aligned, but users should notice it because misleading or overly aggressive outreach could harm recipients or the sender's reputation.
Generate high-converting cold outreach (email, SMS, LinkedIn DM)... The Psychology That Works... Reciprocity... Pattern interrupt... Loss aversion
Use the skill only to draft truthful outreach, avoid deceptive personalization or pressure tactics, and comply with email, SMS, and platform messaging rules.