alterlab-edgartools

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to download regulatory filings and data from the SEC EDGAR system.- [COMMAND_EXECUTION]: It includes methods to launch a local web server for viewing documents (filing.serve) and to open URLs in the system's default web browser (filing.open).- [REMOTE_CODE_EXECUTION]: The MCP server configuration instructions utilize uvx to download and execute the edgartools-mcp package at runtime.- [PROMPT_INJECTION]: As the skill ingests external SEC filings and converts them to Markdown for processing, it exhibits an indirect prompt injection surface (Ingestion points: filings.md, xbrl.md). The capability inventory includes file-system writes (filing.save, filing.download) and local network serving (filing.serve), with no explicit boundary markers or sanitization protocols mentioned in the analyzed documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 12:46 AM
Security Audit — agent-trust-hub — alterlab-edgartools