deep-research

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and processing content from external, untrusted search tools.\n
  • Ingestion points: Research results obtained from Sourcebot, Context7, and Perplexity.\n
  • Boundary markers: The instructions do not specify any delimiters or safety prompts to distinguish external data from system instructions during processing.\n
  • Capability inventory: The skill utilizes tools including codebase_search for local exploration and various mcp__zen tools for architectural analysis and code refactoring.\n
  • Sanitization: There is no evidence of content sanitization or validation of the external research data before it is used to synthesize analysis or implementation plans.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:53 AM