ai-engineer

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes functionality for AI agents that ingest untrusted data from external sources such as web search, API integrations, and document processing. This represents a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in the processed data.
  • Ingestion points: The skill mentions processing data via 'web scraping', 'web search', 'API calls', and 'document processing (PDF, tables)'.
  • Capability inventory: The agent architecture includes tools for 'code execution', 'database queries', and 'API calls'.
  • Boundary markers: The skill proactively addresses these risks by instructing the agent to 'Add guardrails for prompt injection' and 'implement safety measures for responsible AI deployment'.
  • Sanitization: The instructions emphasize 'PII detection and redaction' and 'content moderation' using established APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 06:09 AM