bootstrap
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download Postman CLI installation scripts from the official vendor domain
dl-cli.pstmn.io. These resources are used for initial environment bootstrapping. - [REMOTE_CODE_EXECUTION]: Installation steps include piping remote shell and PowerShell scripts (
unix.sh,win64.ps1) directly to interpreters (shandiex). These scripts are hosted on verified Postman infrastructure. - [COMMAND_EXECUTION]: The skill relies on executing various Postman CLI binaries and commands, such as
postman init,postman login,postman workspace pull/push, andpostman feedbackto perform workspace synchronization and reporting. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from the environment through CLI tool outputs.
- Ingestion points: The agent is instructed to read JSON payloads from
postman init --json,workspace list --json, andworkspace get --json(SKILL.md). - Boundary markers: There are no specific instructions for the agent to use delimiters or ignore potential command sequences embedded in the CLI output.
- Capability inventory: The skill has the capability to execute shell commands, perform package installations via
npm, and write local configuration files (.postman/resources.yaml). - Sanitization: No explicit sanitization or validation of the CLI's JSON output is mandated before the agent interprets the data to determine next steps.
Audit Metadata