The Agent Skills Directory

[COMMAND_EXECUTION]: The skill's activation instructions include a fallback mechanism that executes a local Node.js script: node .aiox-core/development/scripts/unified-activation-pipeline.js qa.
[DYNAMIC_EXECUTION]: The CodeRabbit integration dynamically assembles and executes shell commands based on the host operating system. It uses ~/.local/bin/coderabbit directly on Unix-like systems and wraps commands in wsl bash -c for Windows environments, which is an execution pattern with higher risk if the path or arguments were influenced by untrusted input.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the project repository to influence its behavior.
Ingestion points: The skill reads file content from .aiox/handoffs/, docs/stories/, and metadata from git status, git log, and git diff to construct its persona greeting and command suggestions.
Boundary markers: No explicit sanitization or boundary markers are documented for the data ingested during the activation-instructions logic.
Capability inventory: The skill possesses significant capabilities including shell command execution (git, node, coderabbit), database access (supabase), and web browsing.
Sanitization: There is no evidence of escaping, validation, or filtering of the content read from the file system or git history before it is interpolated into the agent's context.

aiox-qa