alterlab-edgartools

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the edgartools and edgartools[ai] packages from the standard Python package registry using uv pip install. These are legitimate libraries for SEC data access.
  • [COMMAND_EXECUTION]: The skill utilizes Bash(python:*) and uv run python to execute data extraction and processing scripts. This is required for the library's functionality to interact with financial data objects.
  • [INDIRECT_PROMPT_INJECTION]: The skill extracts text and markdown content from external SEC filings to be processed by the AI agent, which is a standard surface for indirect prompt injection.
  • Ingestion points: Filing content is ingested via filing.text(), filing.html(), and filing.markdown() as described in references/filings.md.
  • Boundary markers: The provided examples do not demonstrate the use of specific delimiters or 'ignore' instructions for the extracted text.
  • Capability inventory: The skill has access to Python execution (Bash(python:*)), network access to SEC EDGAR, and filesystem writes (filing.save()).
  • Sanitization: No explicit sanitization or filtering of the external filing content is documented in the code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:36 PM