Skills
Navigate
skills/ouachitalabs/skills/edgartools/Gen Agent Trust Hub

edgartools

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the uv tool to install the edgartools package from the official Python Package Index (PyPI).
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and renders external content from the SEC EDGAR database, creating a surface for indirect prompt injection where malicious text in filings could influence agent actions.
  • Ingestion points: Data is retrieved from the SEC EDGAR API via filing.markdown(), filing.text(), and filing.reports methods described in SKILL.md.
  • Boundary markers: The instructions do not define clear delimiters or provide warnings to ignore instructions embedded within the filing text.
  • Capability inventory: The skill uses Python for file operations (open, write) and the uv tool for package installation.
  • Sanitization: No filtering or sanitization of the external filing data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:24 PM