The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by instructing the agent to fetch and parse external content from Linear ticket URLs.
Ingestion points: Content extracted from external Linear tickets (URLs provided by the user).
Boundary markers: None. The skill does not specify delimiters or instructions to ignore potential commands embedded within the ticket content.
Capability inventory: The agent can execute shell commands (git, pnpm, kubectl, gh), modify local TypeScript configuration files, and create pull requests.
Sanitization: No explicit sanitization or validation steps are defined for the data extracted from Linear tickets before it is used to drive the workflow.
[COMMAND_EXECUTION]: The skill automates several shell commands to manage the deployment lifecycle.
Executes git ls-remote against the hyperlane-xyz/hyperlane-registry repository to synchronize configuration.
Uses pnpm to run project-specific scripts such as update-agent-config:mainnet3 and deploy-warp-monitor.ts.
Utilizes kubectl for monitoring the status of Kubernetes pods and gh for creating pull requests.
While these commands are standard for the intended development workflow, they operate on data derived from external sources (Linear tickets).

warp-deploy-register-route