The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill implements an automated learning system through the teach, recall, and playbook commands. This system records interaction history to synthesize and dynamically execute "playbooks"—sequences of bash commands with variable substitution. This capability for dynamic command assembly from local state introduces potential risks of unintended execution based on manipulated or stale historical data.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the external v0 API via commands such as chats get, chats stream, search, and messages list. This data is provided to the agent without explicit boundary markers or sanitization, creating a surface for indirect prompt injection attacks where malicious content in a chat or message could influence agent behavior.
Ingestion points: External data retrieved from the v0 API through chat, message, and search results (as referenced in SKILL.md).
Boundary markers: None identified in the provided command usage instructions.
Capability inventory: The v0-pp-cli tool possesses capabilities to modify files (update-files), deploy applications (deploy), and register webhooks or MCP servers.
Sanitization: No sanitization or filtering logic is described for the content ingested from the v0 API.- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill requires the installation of a CLI tool via npx -y @mvanhorn/printing-press-library or go install github.com/mvanhorn/printing-press-library/.... These resources originate from the skill's associated vendor infrastructure and are essential for the skill's operation.

pp-v0