OSINT Information

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.9

Overview

This is a straightforward OSINT API wrapper that discloses its remote service and does not show hidden local access, persistence, or destructive behavior.

Install only if you are comfortable sending lookup targets, including email addresses for breach checks, plus your OSINT_API_KEY to osint.ahsan-tariq-ai.xyz. Avoid submitting sensitive client, employee, or third-party identifiers unless you are authorized and have reviewed the provider's privacy, retention, and billing terms.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The top-level description frames the skill as intelligence reports/domain recon, but the documented features also include social username lookup and breach checking, which are materially more privacy-sensitive and can be used for person-focused investigation. This mismatch can mislead users and reviewers into authorizing or invoking the skill without understanding that personal identifiers may be sent to an external OSINT service.

Description-Behavior Mismatch

Medium

• Confidence: 87% confidence
• Finding: The manifest presents the skill as an OSINT reporting and domain recon service, but the declared API also exposes social-media username lookup and breach-by-email endpoints that are not disclosed in the top-level description. This mismatch can mislead reviewers and users about the scope of personal-data processing and enable deployment of higher-risk surveillance or breach-intelligence features without informed scrutiny.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The README explicitly encourages use of sensitive lookups such as domain reconnaissance, social-media lookup, and breach checks against an external API endpoint, but it provides no notice that queried domains, usernames, or email addresses will be transmitted to a third-party service. This creates a real privacy and operational-security risk because users may submit personal data, customer identifiers, or investigative targets without understanding that the data leaves their environment and may be logged, retained, or correlated by the service operator.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The breach-check feature invites users to submit email addresses but does not clearly warn that those addresses are transmitted to an external service. Email addresses are personal data, and sending them to a third-party breach API without explicit notice can create privacy, compliance, and trust risks, especially for non-consenting third parties.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The social lookup feature accepts usernames tied to individuals or accounts, yet the documentation does not explicitly state that these identifiers are sent to an external OSINT API. While lower sensitivity than breach-checked emails, this still creates a transparency issue and can enable unintentional disclosure of investigatory targets to a third party.

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The script sends potentially sensitive identifiers such as domains, usernames, and especially email addresses to a third-party OSINT service without any explicit runtime warning, consent flow, or data-handling notice. In this skill context, external transmission is the core functionality, but the presence of breach lookup and social/domain recon makes the privacy risk more significant because users may unknowingly submit personal or investigative data to an external operator.

VirusTotal

67/67 vendors flagged this skill as clean.