pipefy-process-design
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface in the 'Discovery phase', where it processes user-provided industry context and process requirements. While this constitutes a standard attack surface for indirect prompt injection, the skill's role is restricted to architectural design and information retrieval using
search_pipes, rather than direct file system modifications or external data exfiltration. - [COMMAND_EXECUTION]: The skill uses internal MCP tools
search_pipesandget_organizationfor legitimate discovery purposes. These operations are scoped to the vendor environment and do not allow for arbitrary shell command execution or system-level access. - [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts. References to other skills (e.g.,
pipefy-building) are internal relative file paths used for agent routing rather than remote resource fetching.
Audit Metadata