analyst-common

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (SAFE): The skill contains no instructions designed to bypass agent safety or override system constraints. The use of 'CRITICAL' and 'MANDATORY' labels is appropriately used to enforce data verification logic.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials or data exfiltration patterns were detected. The skill explicitly limits data sources to a predefined allowlist of reputable financial institutions.
  • Indirect Prompt Injection (LOW):
  • Ingestion points: External data is ingested through the mcp_websearch_web_search_exa and WebFetch tools as specified in SKILL.md.
  • Boundary markers: Absent. There are no specific instructions to treat web content as untrusted data or use delimiters.
  • Capability inventory: The skill uses web search and fetching tools but lacks file-writing or code-execution capabilities.
  • Sanitization: No specific sanitization or filtering of search result content is mentioned.
  • Remote Code Execution (SAFE): No patterns for remote script execution, unauthorized package installation, or dynamic code evaluation were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 05:46 PM