The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill defines workflows that ingest untrusted external data which could potentially influence agent behavior.
Ingestion points: The skill reads live service logs via railway logs and environment variables via railway variables.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided patterns.
Capability inventory: The skill possesses extensive local execution capabilities, including shell command execution (railway, pnpm, git, gh), database migration deployment, and network requests (curl).
Sanitization: There is no evidence of sanitization or validation logic for the data processed during log analysis or variable management.

tzurot-deployment