postman

Warn

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill setup documentation suggests persisting the Postman API key in shell configuration files like ~/.zshrc or ~/.bashrc, which exposes the credential to any process that can read these files.
  • [COMMAND_EXECUTION]: The agent is granted access to high-capability tools including Bash, which is used for setup tasks that establish persistence for environment variables.
  • [PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection from processing external data.
  • Ingestion points: Local OpenAPI files (openapi.json, swagger.yaml) and remote Postman API data are ingested during sync and generation workflows.
  • Boundary markers: No boundary markers or 'ignore embedded instruction' warnings are present to isolate external content.
  • Capability inventory: The skill allows file system writing (Write) and comprehensive API interaction (mcp__postman__*), which could be misused if malicious instructions are processed.
  • Sanitization: There is no evidence of sanitization or filtering applied to external content before it is interpolated into prompts for code generation or documentation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 02:57 PM