The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the openalex-pp-cli binary using npx from the @mvanhorn/printing-press-library package and via go install from the github.com/mvanhorn/printing-press-library repository. These resources are part of the vendor's established infrastructure.
[COMMAND_EXECUTION]: The skill invokes the openalex-pp-cli tool through the Bash tool to perform research graph retrieval, metadata searching, and tool diagnostics.
[DATA_EXFILTRATION]: The CLI tool supports a --deliver webhook:<url> flag, which allows the output of search and analysis commands to be POSTed directly to external network endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted scholarly data (titles, abstracts, and author information) from the OpenAlex API, creating an attack surface where malicious content in papers could influence agent behavior.
Ingestion points: Scholarly work records, author profiles, and metadata returned by the OpenAlex API (SKILL.md).
Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions that might be embedded in the retrieved scholarly content.
Capability inventory: Subprocess execution of the openalex-pp-cli binary, file system writing via the --deliver file flag, and network exfiltration via the --deliver webhook flag (SKILL.md).
Sanitization: Absent; external data is incorporated into the agent's context without explicit filtering or sanitization of embedded natural language instructions.

pp-openalex