The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the postman-explore-pp-cli and postman-explore-pp-mcp tools from the vendor's NPM registry (@mvanhorn/printing-press-library) and GitHub repository (github.com/mvanhorn/printing-press-library).- [COMMAND_EXECUTION]: The skill relies on executing the postman-explore-pp-cli binary with various subcommands such as canonical, top, drift, and sync to interact with the Postman network.- [DATA_EXFILTRATION]: The CLI includes a --deliver webhook:<url> feature that allows the agent to send command output to an external URL, which represents a potential vector for data exfiltration if the agent is directed to use an untrusted endpoint.- [INDIRECT_PROMPT_INJECTION]: The skill processes community-contributed content (collections, workspaces, APIs) from the Postman public network, creating a surface for indirect prompt injection.
Ingestion points: External data is ingested via the browse, search-all, and networkentity commands from postman.com/explore.
Boundary markers: The CLI uses structured JSON output, but no explicit instruction-isolation boundaries or sanitization warnings are documented.
Capability inventory: The skill environment allows for subprocess execution, local file writing (--deliver file:), and outbound network requests (--deliver webhook:).
Sanitization: There is no documented sanitization or filtering of community-contributed text fields before they are presented to the agent.

pp-postman-explore