pagerduty-automation
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from PagerDuty incidents, alerts, and notes, creating a potential vector for indirect prompt injection where malicious content in an incident could attempt to hijack the agent's context.
- Ingestion points: Data enters the agent's context via tools such as
PAGERDUTY_FETCH_INCIDENT_LIST,PAGERDUTY_GET_ALERTS_BY_INCIDENT_ID, andPAGERDUTY_RETRIEVE_INCIDENT_BY_INCIDENT_ID(SKILL.md). - Boundary markers: The instructions do not specify any delimiters or boundary markers to help the agent distinguish between its system instructions and the data retrieved from PagerDuty.
- Capability inventory: The skill has significant capabilities to modify the environment, including
PAGERDUTY_UPDATE_INCIDENT_BY_ID,PAGERDUTY_POST_INCIDENT_NOTE_USING_ID, and tools for managing services, schedules, and escalation policies (SKILL.md). - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the data retrieved from external PagerDuty APIs before it is interpreted by the agent.
Audit Metadata