questioning

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill functions as a research assistant, utilizing codebase analysis and web search to provide users with direct answers. All operations, including sub-agent invocation and file creation, are transparent and align with its documented purpose.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection due to its processing of untrusted local and external data.
  • Ingestion points: Local codebase files (Step 2), web search results (Step 2), and documentation fetched via context7 MCP.
  • Boundary markers: No explicit delimiters or instructions are used to sandbox the data retrieved from external or local sources.
  • Capability inventory: The skill can invoke specialized sub-agents (codebase-locator, web-search-researcher) and write Markdown files to the thoughts directory.
  • Sanitization: There is no evidence of sanitization or safety checks performed on the data before it is presented to the user or saved to the file system.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 09:43 PM