financial-analysis-comps

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves financial data from well-known services including SEC EDGAR (data.sec.gov) and Yahoo Finance (query1.finance.yahoo.com) using the Python standard library. These requests are consistent with the skill's stated purpose of financial benchmarking.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external financial APIs, which could theoretically contain malicious instructions.
  • Ingestion points: Financial metrics, company names, and period labels are fetched in scripts/get_fundamentals.py and scripts/get_quote.py.
  • Boundary markers: The instructions do not define clear delimiters for the ingested data to prevent the agent from interpreting it as instructions.
  • Capability inventory: The skill scripts perform network requests and data calculations across multiple files.
  • Sanitization: The skill processes and displays external strings (like entity names) without validation or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:38 PM
Security Audit — agent-trust-hub — financial-analysis-comps