skills/postmanlabs/skills/api-builder/Gen Agent Trust Hub

api-builder

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process OpenAPI specifications and Postman collection files from the local repository. This creates an attack surface where an attacker who can modify these files could embed hidden instructions to manipulate the agent's behavior.
  • Ingestion points: OpenAPI specs located in postman/specs/ and collection/environment YAML files in postman/collections/ and postman/environments/.
  • Boundary markers: The instructions do not define clear delimiters or provide instructions to the agent to ignore embedded natural language commands within the data files.
  • Capability inventory: The agent is authorized to perform file system operations (read/write) and execute shell commands via the postman CLI.
  • Sanitization: The skill relies on YAML schema validation but does not specify sanitization for natural language instructions that might be present in descriptions or other metadata fields.
  • [DYNAMIC_EXECUTION]: The Postman Collection v3 schema documentation explicitly supports fields that contain executable code or commands which the agent is expected to handle.
  • Evidence: In reference/collection_schema_v3.md, the scripts field for collections and requests allows for text/javascript code. Additionally, the MCP Request schema includes a STDIO transport definition containing a command field and an env array for environment variables, which facilitates the execution of external processes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:44 AM