The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes event orchestration data from PagerDuty, which acts as an external ingestion point for untrusted content that could influence agent behavior.
Ingestion points: Data is ingested through tools like get_event_orchestration, get_event_orchestration_router, and get_event_orchestration_service which query the PagerDuty API.
Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the retrieved PagerDuty rules.
Capability inventory: The skill has the ability to modify PagerDuty configurations using update_event_orchestration_router and append_event_orchestration_router_rule.
Sanitization: No sanitization or validation steps are described for the data fetched from the external API.
[EXTERNAL_DOWNLOADS]: The skill fetches the pagerduty-mcp package at runtime via the uvx tool to provide its server functionality.
[METADATA_POISONING]: There is a discrepancy between the author listed in the metadata (netclaw) and the expected vendor identification (automateyournetwork).

pagerduty-orchestration