sf-ai-agentscript
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The syntax validator script
hooks/scripts/agentscript-syntax-validator.pyutilizes thesubprocess.runmethod to invoke the Salesforce CLI (sf). This behavior is benign as it is used solely to validate the agent configuration against the user's Salesforce environment. - [PROMPT_INJECTION]: Static analysis flagged prompt injection patterns in
references/fsm-architecture.md; however, these are used for educational purposes to describe platform guardrails and do not constitute an actual injection attempt. - [DATA_EXPOSURE]: No hardcoded credentials or sensitive file paths were discovered. The skill follows best practices by using linked variables for session context and placeholders for user-specific configurations.
Audit Metadata