pagerduty-orchestration

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes event orchestration and routing data from PagerDuty, which serves as an external source (Category 8). This creates a potential surface where maliciously crafted content within the PagerDuty account could influence the agent's actions. \n
  • Ingestion points: The agent retrieves data through the list_event_orchestrations, get_event_orchestration, and get_event_orchestration_router tools defined in SKILL.md. \n
  • Boundary markers: None; the instructions lack specific delimiters or guardrails to prevent the agent from obeying instructions embedded in the external API responses. \n
  • Capability inventory: The skill includes high-privilege write tools such as update_event_orchestration_router and append_event_orchestration_router_rule in SKILL.md. \n
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from PagerDuty. \n- [EXTERNAL_DOWNLOADS]: The skill uses the pagerduty-mcp server package, which is fetched from an external registry at runtime. \n- [COMMAND_EXECUTION]: The skill utilizes the uvx tool to execute the pagerduty-mcp server process for handling API communications.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:29 PM
Security Audit — agent-trust-hub — pagerduty-orchestration