The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructions identify a potential surface for indirect prompt injection because the agent is tasked with processing and analyzing external dispatcher configuration files and runtime logs. This capability is inherent to the skill's purpose of auditing and troubleshooting AEM environments.\n
Ingestion points: Configuration files located in the dispatcher/src directory and log data retrieved via the tail_logs tool.\n
Boundary markers: The playbooks and workflows include explicit verification gates, such as mandatory static validation and runtime evidence requirements, which act as safeguards against unintended obedience to instructions embedded in processed data.\n
Capability inventory: The skill utilizes a set of MCP tools (validate, lint, sdk, trace_request, inspect_cache, monitor_metrics, tail_logs) that provide the agent with the ability to read project files and perform network probes within the target environment.\n
Sanitization: The workflow mandates the use of static analysis tools (validate, lint) to verify content before recommendations are finalized.

dispatcher