The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches and installs the is-agentic-pp-cli tool using npx from the @mvanhorn/printing-press-library package and via go install from the vendor's repository at github.com/mvanhorn/printing-press-library.
[DYNAMIC_EXECUTION]: Implements a playbook system through the recall and teach commands where the CLI returns a sequence of shell commands (Playbook.steps) to the agent. The instructions direct the agent to execute these commands, which are synthesized and stored in the CLI's local database from previous operations.
[DATA_EXFILTRATION]: Includes a --deliver webhook:<url> flag that POSTs command output to an arbitrary external URL. This creates a potential path for exfiltrating data processed by the skill to external endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from public websites and incorporates it into a local learning loop. This ingestion surface, combined with the ability to generate future command playbooks based on that data, presents an indirect prompt injection risk.
[REMOTE_CODE_EXECUTION]: The skill provides instructions to download and execute code from remote repositories via npx and go install to set up the necessary CLI and MCP binaries.

pp-is-agentic