The Agent Skills Directory

[COMMAND_EXECUTION]: The skill documentation provides instructions for the agent to execute local shell and Python scripts, specifically workflow_engine/hook_runner.sh and workflow_engine/runner.py, to manage the state machine and automate development tasks.- [EXTERNAL_DOWNLOADS]: The documentation identifies a requirement for inotify-tools, a well-known Linux utility used for monitoring file system events, which may need to be installed on the host system.- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it is designed to ingest and process untrusted data from an external file (user_request.json).
Ingestion points: User requirements are loaded from user_request.json and passed through five sequential agent steps as described in SKILL.md.
Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to separate user data from agent prompts.
Capability inventory: The skill has the capability to write files, generate code patches, and execute commands via its orchestration engine.
Sanitization: There is no mention of input validation or content filtering for the data ingested from the requirement files.

workflow-orchestrator