catalyst-datastore

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents methods for ingesting and processing data that could originate from untrusted sources, creating a potential surface for indirect prompt injection.
  • Ingestion points: The skill references userInput in the stripEmoji function and handles data for insertRow and executeZCQLQuery operations in references/datastore-basics.md.
  • Boundary markers: No specific delimiters (like XML tags or multi-line separators) are suggested to isolate external data from the agent's instructions.
  • Capability inventory: The skill utilizes powerful capabilities including CatalystbyZoho_Create_Table and executeZCQLQuery (via MCP tools) and SDK methods for CRUD operations (insertRow, updateRow, deleteRow) in references/datastore-basics.md.
  • Sanitization: The skill provides a stripEmoji function to sanitize 4-byte UTF-8 characters but does not provide generalized input validation or escaping mechanisms for ZCQL queries.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 07:15 AM
Security Audit — agent-trust-hub — catalyst-datastore