The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze LocalStack emulator logs, which represents an indirect prompt injection surface as log content could contain arbitrary data from AWS API interactions.
Ingestion points: Terminal output from lstk logs and lstk status as described in SKILL.md.
Boundary markers: No specific delimiters are defined for separating log content from agent instructions.
Capability inventory: The skill uses lstk for log retrieval, grep for filtering, and curl for health checks against localhost.
Sanitization: No explicit sanitization of log content is performed before analysis.
[COMMAND_EXECUTION]: The skill uses standard CLI tools (lstk, grep, curl) to interact with a local LocalStack instance, which is the intended behavior for an emulator debugging tool.

localstack-logs