pipefy-portal-setup
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of legitimate instructions for managing Pipefy's own platform. It is authored by the vendor and uses standard authentication and configuration patterns. All external references point to official vendor-owned GitHub repositories and documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Pipefy API, which constitutes an attack surface for indirect prompt injection. Maliciously crafted content within a Pipefy portal could theoretically attempt to influence agent behavior through tools that read portal structure.
- Ingestion points: Portal names, page titles, and element metadata retrieved via
list_portalsandget_portaltools (SKILL.md). - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation for handling API data.
- Capability inventory: The skill provides comprehensive write access, including creating, updating, and deleting portals, pages, and elements (SKILL.md, references/cli.md).
- Sanitization: The instructions do not define explicit validation or sanitization steps for data returned from the API before it enters the agent context.
Audit Metadata