sector-rotation

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external macro news which constitutes a surface for indirect prompt injection. * Ingestion points: The skill uses the search_news tool to ingest macro-economic data (SKILL.md). * Boundary markers: There are no specific delimiters or instructions to ignore embedded commands within the retrieved news data. * Capability inventory: The skill is only permitted to use get_market_overview, get_sector_data, and search_news, which are read-only tools with no capability to write files, execute commands, or perform network requests to external domains. * Sanitization: No sanitization or content validation is applied to the retrieved news data.
  • [SAFE]: The skill instructions and workflow are consistent with its stated purpose of market analysis. No patterns of obfuscation, credential theft, privilege escalation, or persistence were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 08:26 PM