pagerduty-api
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools to ingest data from PagerDuty resources that contain untrusted content provided by external users, such as incident notes and status updates. This creates a vulnerability surface where malicious instructions embedded in PagerDuty data could influence the agent's actions.
- Ingestion points:
references/operations/getIncident.md,references/operations/getIncidentNote.md,references/operations/getIncidentFieldValues.md. - Boundary markers: Absent. The documentation does not specify the use of delimiters or instructions to ignore embedded commands within the fetched data.
- Capability inventory: The skill exposes high-privilege capabilities including user creation (
createUser.md), automation action management (createAutomationAction.md), service deletion (deleteService.md), and webhook configuration (createWebhookSubscription.md). - Sanitization: Absent. There is no mention of sanitizing or validating external content before it is processed by the agent.
Audit Metadata