Salesforce AI Agentforce Testing

Agentforce agent testing with dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates tes...

This skill appears to implement what it claims (Agentforce test execution, coverage, and an automated fix loop) but includes executable scripts that manage credentials and can modify agents in your org. Before installing or running it: 1) Review the shipped scripts (especially credential_manager.py, run-automated-tests.py, multi_turn_test_runner.py, and any code that calls sf or the Agent Runtime API) to confirm they do not exfiltrate tokens or call unexpected endpoints. 2) Only provide credentials for a safe test/dev org; do not reuse production admin keys. 3) If you will not allow automatic fixes or republishing, disable or require explicit confirmation for the 'agentic fix loop'. 4) Prefer interactive sf org login (web) where possible rather than storing ECA credentials in files or env vars. 5) If you lack the ability to audit the scripts, run the skill in a sandboxed/test environment first and monitor network calls and API activity. If you want, I can scan specific script files (credential_manager.py, run-automated-tests.py) and summarize any risky operations (network endpoints, file system writes, subprocess execution).

Type: OpenClaw Skill Name: sf-ai-agentforce-testing Version: 1.0.0 The sf-ai-agentforce-testing skill bundle is a comprehensive toolset for testing Salesforce Agentforce agents. It includes Python scripts for metadata discovery (agent_discovery.py), a secure local credential manager (credential_manager.py), and a multi-turn conversation test runner (multi_turn_test_runner.py). The bundle facilitates both single-utterance CLI tests and complex multi-turn API interactions using the official Salesforce Agent Runtime API. The code uses standard libraries and the Salesforce CLI (sf) to perform its tasks, and the credential management implementation follows security best practices by using restricted file permissions (0600) and local storage (~/.sfagent/). No evidence of malicious intent, data exfiltration, or prompt injection was found.