The Agent Skills Directory

[PROMPT_INJECTION]: Indirect Prompt Injection Surface.
Ingestion points: The skill ingests data from external Monte Carlo alerts via the get_alerts tool and troubleshooting summaries from run_troubleshooting_agent.
Boundary markers: The instructions lack explicit boundary markers or directives to the agent to disregard instructions potentially embedded within the alert metadata or troubleshooting logs.
Capability inventory: The skill utilizes tools with write capabilities (update_alert, set_alert_owner, create_or_update_alert_comment, mark_event_as_normal) and permits writing workflow files to the local file system.
Sanitization: There is no evidence of content sanitization or validation for the data retrieved from external tools before it is used to influence agent decisions.

automated-triage