financial-analysis-earnings-preview

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves financial statement data directly from official U.S. government domains (sec.gov) using Python's standard library. These are well-known, trusted sources for financial research.
  • [COMMAND_EXECUTION]: The workflow involves running a local Python script via a shell wrapper (run.sh). Analysis confirms the use of secure argument passing ($@) and robust parsing (argparse), which prevents command injection from user-provided stock symbols.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web search results (SKILL.md) and API responses (get_fundamentals.py). While explicit boundary markers are absent, the risk is minimal as capabilities are limited to analytical processing and input symbols are validated against an authoritative SEC mapping before use.
  • [SAFE]: The implementation is self-contained with no third-party package dependencies and includes a built-in request throttling mechanism (8 requests/second) to ensure compliance with SEC fair access guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:38 PM
Security Audit — agent-trust-hub — financial-analysis-earnings-preview