osint-tools-mcp-server

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation process involves cloning code from multiple GitHub repositories not associated with trusted organizations, including repositories under the accounts frishtik, smicallef, mxrch, and p1ngul1n0.
  • [COMMAND_EXECUTION]: The skill wraps several command-line tools (Sherlock, Holehe, SpiderFoot, etc.) and executes them as subprocesses using inputs provided by the user, such as target domains, emails, or usernames.
  • [REMOTE_CODE_EXECUTION]: Code examples for extending the skill demonstrate building command arguments by splitting user-controlled strings (e.g., cmd.extend(options.split())). This pattern is a significant command injection risk if the user input is not strictly validated.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Untrusted data retrieved from social media profiles, search engines, and public websites by tools like Sherlock and Maigret. Boundary markers: None identified. Capability inventory: Execution of external CLI tools via asyncio.create_subprocess_exec. Sanitization: No sanitization or filtering of the retrieved data is mentioned before it is processed by the AI agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 10:43 PM
Security Audit — agent-trust-hub — osint-tools-mcp-server