pipefy-database-tables
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill mandates a security-first approach for destructive operations such as delete_table, delete_table_field, and delete_table_record. It requires a two-step process where the agent must present a preview and a confirmation token to the user for explicit approval before execution.
- [SAFE]: The tool upload_attachment_to_table_record includes built-in protection against Server-Side Request Forgery (SSRF) when handling remote file URLs, which is a key security practice for agentic tools processing external links.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with user-controlled database content which presents a potential injection surface. 1. Ingestion points: Data is ingested through tools like get_table_records, find_records, and get_table_record from the Pipefy platform. 2. Boundary markers: The instructions do not define specific delimiters for separating record data from agent instructions. 3. Capability inventory: The skill allows for data modification (CRUD) and file uploads to the Pipefy environment. 4. Sanitization: While field-level text sanitization is not specified, the skill implements SSRF-guarding for external URL sources.
Audit Metadata