hedwigai

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest, analyze, and summarize data from a wide variety of external public records.
  • Ingestion points: Fetches data from primary sources including SEC filings, trademark registers, FDA records, import logs, and web traffic metrics (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or warnings to the agent regarding potential instructions embedded within the record data.
  • Capability inventory: The skill has access to a bash tool for executing data programs and a create_workbook tool for writing research reports (SKILL.md).
  • Sanitization: There are no documented procedures for sanitizing or escaping the content retrieved from external public records before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill utilizes a bash tool to run various research programs (e.g., traffic, rank, company-hiring). The instructions characterize this as a read-only shell environment dedicated to these specific data programs.
  • [EXTERNAL_DOWNLOADS]: The skill references an external Model Context Protocol (MCP) server located at https://mcp.hedwigai.com/ and provides instructions for installing supplementary plugins from the un-seen namespace. These represent the infrastructure and resources of the skill's vendor.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 10:53 AM