financial-analysis-earnings

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected in the skill instructions or scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web search results and external financial APIs.
  • Ingestion points: Web search results (SKILL.md), SEC EDGAR XBRL API (get_fundamentals.py), and Yahoo Finance endpoints (get_quote.py).
  • Boundary markers: None explicitly implemented to delimit untrusted data in the prompt context.
  • Capability inventory: Shell execution via run.sh to trigger local Python scripts and network operations using urllib.request to fetch data from known financial domains.
  • Sanitization: No specific sanitization or filtering is applied to the incoming JSON/text data before processing.
  • Assessment: This is a low-risk functional surface inherent to data retrieval tools; the skill does not possess high-privilege capabilities that would make this vulnerability critical.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:37 PM
Security Audit — agent-trust-hub — financial-analysis-earnings