The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the uvx tool to download and run the pagerduty-mcp package from the Python Package Index (PyPI). This is a standard and safe method for executing Model Context Protocol (MCP) servers using code from well-known repositories.
[COMMAND_EXECUTION]: The skill executes the uvx pagerduty-mcp command to initialize the server. This command is necessary for the skill's intended functionality.
[PROMPT_INJECTION]: The skill retrieves incident notes and alerts from PagerDuty, which constitutes a potential surface for indirect prompt injection. 1. Ingestion points: External data is ingested through tools like get_incident and list_incident_notes. 2. Boundary markers: No explicit markers are defined in the instructions to delimit external content. 3. Capability inventory: The skill includes write capabilities such as manage_incidents, add_note_to_incident, and add_responders. 4. Sanitization: No description of data sanitization or validation is provided for the retrieved PagerDuty content.

pagerduty-incidents