postman-mcp-server
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes external data from OpenAPI specifications and Postman collections, which creates a surface for potential indirect prompt injection attacks where malicious instructions could be embedded in the documentation.\n
- Ingestion points: The skill reads local files (OpenAPI/Swagger definitions) and fetches remote content through tools like
getSpecDefinitionandgetCollection.\n - Boundary markers: There are no explicit instructions or delimiters defined to separate the untrusted external content from the agent's core instructions.\n
- Capability inventory: The skill has permissions to write to local files (e.g., creating
docs/api-reference.mdor updating spec files) and execute network requests through the Postman MCP toolset.\n - Sanitization: The documentation does not specify any sanitization, validation, or escaping logic for the external content before it is processed by the agent.
Audit Metadata