pipefy-automations
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documents standard functionality for managing Pipefy automations via MCP tools. It does not contain any executable code, remote downloads, or obfuscated content.
- [INDIRECT_PROMPT_INJECTION]: The skill documents a surface for indirect prompt injection via the
create_ai_automationtool, which processes field data using AI. However, it includes mandatory boundary markers and validation steps (thevalidate_ai_automation_prompttool) to mitigate risks. Severity is assessed as safe/low as it represents documented platform functionality. - [COMMAND_EXECUTION]: While the skill mentions CLI commands (e.g.,
pipefy automation list), these are provided as references for the user and are not executed automatically by the agent. - [CREDENTIALS_SAFE]: The skill correctly instructs the user to discover numeric internal IDs rather than using hardcoded secrets or sensitive tokens. It does not request or store credentials.
- [DATA_EXFILTRATION]: No network operations to non-vendor domains or sensitive file access patterns were found. All documented tools and processes are contained within the Pipefy ecosystem.
Audit Metadata