Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward lead-research helper that uses a disclosed external backend, with no hidden persistence, privilege escalation, or unrelated behavior found.
Before installing, be aware that lead inputs such as company and target persona, plus any API key you provide, are sent to the skill publisher's external backend. Avoid entering confidential prospect notes or sensitive credentials unless you trust that backend and its data practices.
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
[One punchy cold email or DM opener tailored to persona]
---
## Output Guidelines
- Be specific, not generic
- Prioritize sales relevance
- Keep each section concise and scannable
The skill instructs the agent to send user-supplied company/persona data and an access token to a third-party backend, but it provides no user-facing disclosure, consent step, or data-handling constraints. This creates a real privacy and credential-handling risk because users may not realize their inputs and token are being transmitted off-platform to an external service.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
"company": "HubSpot",
"persona": "Head of Sales"
}
r = requests.post(f"{BASE_URL}/analyze-lead", json=payload, headers=headers)
data = r.json()
print("Status:", r.status_code)
This code sends data to a remote service using a custom access-token header and a JSON payload, but the file provides no warning about transmitting user or system data beyond generic test labels. For code files, network calls that transmit data should have some visible disclosure such as a comment, docstring, or user-facing notice unless the transmission is clearly explained as part of the skill's purpose.
No suspicious patterns detected.