The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/health-lint.py script executes local shell commands (specifically git, wc, and awk) to perform repository analysis, identify changed files, and verify submodule pointers. These calls use argument lists rather than shell strings and do not use shell=True, which follows best practices for preventing command injection.
[INDIRECT_PROMPT_INJECTION]: The skill acts as an orchestrator that reads and processes project documentation files from docs/devdocs/. This represents a potential attack surface where malicious instructions embedded in the documentation could attempt to influence the agent's routing logic or the behavior of sub-agents. The skill mitigates this risk by broadcasting routing decisions to the user for confirmation and by using a structured task handoff mechanism (yaml-summary-v1) that limits the context passed between different agents.

pipeline