finance-expert

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a comprehensive knowledge base and operational instructions for financial modeling and SaaS metrics. No evidence of malicious intent or security bypass attempts was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill utilizes tools such as WebSearch, WebFetch, and mcp__scout to ingest untrusted data from the web. This creates a potential surface for indirect prompt injection attacks.
  • Ingestion points: Tools WebFetch, WebSearch, and mcp__scout__readable_text allow external data to enter the agent context.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the fetched content.
  • Capability inventory: The skill is limited to reading files (Read, Glob, Grep) and fetching web data; it does not have capabilities for file modification, code execution, or privilege escalation.
  • Sanitization: There are no explicit sanitization or validation steps defined for the data retrieved via the search and fetch tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 10:20 AM
Security Audit — agent-trust-hub — finance-expert