The Agent Skills Directory

[PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by accepting the user's environment argument and surrounding request as command input.
Ingestion points: User-supplied [environment] and "surrounding request" parameters described in SKILL.md.
Boundary markers: Absent; there are no instructions for the agent to ignore or delimit instructions found within the user input.
Capability inventory: The skill is intended to monitor health endpoints, logs, errors, and performance data.
Sanitization: No validation or sanitization of the user-provided arguments is specified.
[NO_CODE]: This skill consists entirely of instructional markdown and does not include any scripts, executables, or code files.

lisa-monitor