skills/connic-org/connic-skill/connic/Gen Agent Trust Hub

connic

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill includes detailed instructions for implementing input and output guardrails, including built-in types for blocking prompt injection and system prompt leakage.
  • [EXTERNAL_DOWNLOADS]: Documents the installation of the official connic-composer-sdk via standard package managers and directs users to canonical documentation at connic.co.
  • [COMMAND_EXECUTION]: Describes legitimate usage of the connic CLI for common developer workflows such as linting project files, running test suites, and deploying code to isolated environments.
  • [DATA_EXFILTRATION]: Details the platform's ability to interface with databases and the web, while providing explicit best practices to wrap these operations in purpose-driven tools to minimize data exposure.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:22 PM
Security Audit — agent-trust-hub — connic