ClawHub
Back to skill

Security audit

Pangolinfo Scrape (Legacy)

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Pangolin API helper, with expected credential use and remote search/scrape requests, but users should treat tokens and submitted queries as sensitive.

Install only if you are comfortable sending the searches, URLs, follow-up prompts, zip code, and any requested screenshots to Pangolin. Use a dedicated or revocable token when possible, avoid confidential searches, and remove or rotate ~/.pangolin_token if used on a shared machine.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
97% confidence
Finding
The skill documentation describes capabilities that require access to environment variables, local files, shell execution, and outbound network access, but it does not declare permissions explicitly. This creates a transparency and governance gap: a user or hosting platform may grant or invoke the skill without understanding that it will read credentials, cache tokens to disk, and contact external services, increasing the risk of unintended credential use or data exfiltration.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill states that `PANGOLIN_EMAIL`, `PANGOLIN_PASSWORD`, or `PANGOLIN_TOKEN` are required, but does not explicitly warn that these secrets will be used to authenticate to a third-party service and enable API calls on the user's account. In practice this can cause users to supply sensitive credentials without informed consent about where they are sent, what account actions they authorize, or that usage may incur billable API credits.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation instructs users to send search queries and follow-up prompts to a third-party scraping endpoint, but it does not warn that potentially sensitive user input will leave the local environment and be processed by an external service. In a skill designed for programmatic search and multi-turn dialogue, this increases the chance that users unknowingly transmit confidential prompts, internal research topics, or personal data to a vendor-controlled endpoint.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.