The Agent Skills Directory

[SAFE]: The skill contains no malicious code, hardcoded secrets, or suspicious behavior. It uses standard transport and configuration for PagerDuty interaction.
[EXTERNAL_DOWNLOADS]: The skill specifies the use of the pagerduty-mcp server package via uvx. This is a standard method for executing MCP servers and is consistent with the skill's documented purpose.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes metadata from external PagerDuty services.
Ingestion points: External data is ingested through the list_services and get_service tools as defined in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to treat tool outputs as untrusted data.
Capability inventory: The skill includes tools for modifying state, including create_service and update_service.
Sanitization: No validation or sanitization of the PagerDuty API responses is performed within the skill definition.

pagerduty-services