pipefy-introspection
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of the
pipefyCLI tool and raw GraphQL queries against the vendor's API endpoints. This is the primary intended functionality for introspection and fallback operations. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for processing untrusted data by ingesting responses directly from the external Pipefy API.
- Ingestion points: API responses returned by
execute_graphql,introspect_type, and other discovery tools in thepipefy-introspectionskill. - Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the API response data.
- Capability inventory: The skill possesses the capability to perform network operations and data modifications via the Pipefy GraphQL API.
- Sanitization: The skill incorporates a robust safety mechanism requiring a two-step confirmation process (preview followed by a token-verified execution) for all mutation operations.
Audit Metadata