ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Cold Email Writer

v1.1.0

Writes personalized cold emails that actually get replies

⭐ 0· 695·0 current·0 all-time
by@1kalin
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description match the SKILL.md. There are no declared env vars, binaries, or install steps that would be unnecessary for a text-generation/instruction skill; everything asked for (recipient, offer, problems, personalization) is relevant to producing personalized cold emails.
✓
Instruction Scope
SKILL.md contains only guidance for composing emails, personalization tiers, and a checklist. It does not instruct the agent to read system files, access environment variables, invoke external APIs, or transmit data to unexpected endpoints. It does include marketing links to AfrexAI pages but those are external references, not runtime exfiltration instructions.
✓
Install Mechanism
No install spec and no code files — instruction-only content. This is the lowest-risk install profile (nothing is written to disk or executed).
✓
Credentials
No required environment variables, credentials, or config paths are declared or referenced; the skill does not request secrets or unrelated credentials.
✓
Persistence & Privilege
Flags show default behavior (always:false, agent-invocable allowed). The skill does not request permanent presence or to modify other skills or system settings.
Assessment
This skill is a straightforward guide for composing cold outreach; it does not access your system or request credentials. Before using output in real outreach, review each message for accuracy, privacy, and compliance: remove any accidental inclusion of sensitive data, confirm you have the right to contact recipients, and ensure messages comply with anti-spam laws and company policy. If you want the agent to actually send emails, that will require separate mail-sending integrations (SMTP/Gmail/CRM) and associated credentials — expect those to be requested at that time and review them for proportionality. Finally, avoid using the skill to automate harassment or illegal activity; keep personalization ethical and consent-respecting.

Like a lobster shell, security has layers — review code before you run it.

latestvk9748cyvwq8syzw3y41m5w45w5812zjd

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments