suggesting-data-imports

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external database sources, which introduces a surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context through posthog:execute-sql results, including table metadata and record content.
  • Boundary markers: The instructions do not provide specific delimiters or ignore-instructions markers to isolate data from agent logic.
  • Capability inventory: The skill has access to tools that can list external sources, fetch schemas, and execute SQL queries.
  • Sanitization: The skill lacks explicit instructions for sanitizing or validating external data before the agent uses it for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:22 PM
Security Audit — agent-trust-hub — suggesting-data-imports