The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill executes local Nx commands using secure subprocess patterns.
Evidence: All handlers in nx.py use subprocess.run with argument lists (tuples) instead of shell strings.
Mitigation: This prevents shell injection attacks where an attacker might try to run additional commands using shell syntax like ; or &&.
[PROMPT_INJECTION] (LOW): The skill exposes a surface for indirect prompt injection by reading workspace configuration and command outputs.
Ingestion points: Workspace metadata from nx show and command results from nx run-many (found in nx.py).
Boundary markers: The skill does not use specific delimiters or instructions to ignore nested commands in the workspace data.
Capability inventory: The skill has the ability to execute various shell-based commands through its command handlers.
Sanitization: No sanitization is performed on the data retrieved from the workspace. This is a common surface for workspace tools and is considered a low risk for this use case.

nx-tools