The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes a local Python script tools/brain.py using uv run to log summaries of monitoring results. This script is located via the $CLAUDE_PROJECT_DIR environment variable.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data during its monitoring routine, creating a surface for indirect prompt injection.
Ingestion points: The skill analyzes external host discovery data, JavaScript bundles, API response schemas, and program scope text fetched from the platform (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions to treat ingested content as data rather than instructions within the logic.
Capability inventory: The skill has the capability to execute shell commands using uv run for logging purposes (SKILL.md).
Sanitization: The skill does not describe any sanitization, validation, or escaping of the external data before it is processed by the agent or logged to the 'brain' tool.

monitor