add-datasource

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection: The skill utilizes natural language input to map user requests to specific tool invocations.
  • Ingestion points: The skill ingests data through the AskUserQuestion tool and the $ARGUMENTS variable.
  • Boundary markers: The instructions do not employ specific delimiters or isolation techniques for the user-provided goals.
  • Capability inventory: The skill has access to tools for file modification (Write, Edit), shell execution (Bash), and skill delegation (Skill), which are utilized based on interpreted input.
  • Sanitization: User input is directly evaluated by the routing logic without additional sanitization or schema enforcement.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:15 AM
Security Audit — agent-trust-hub — add-datasource