pagerduty
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches data from the official PagerDuty API at
api.pagerduty.com. This is a well-known service and the communication is restricted to read-only operations. - [COMMAND_EXECUTION]: Executes standard CLI tools including
curlfor network requests,jqfor JSON processing, anddatefor time calculations. These are expected tools for a monitoring integration. - [INDIRECT_PROMPT_INJECTION]: The skill represents a potential attack surface for indirect prompt injection as it processes external API data.
- Ingestion points: Incident notes and log entries fetched via endpoints like
/incidents/<id>/log_entriesand/notes(SKILL.md). - Boundary markers: Absent; there are no specific instructions to wrap external data in delimiters.
- Capability inventory: Uses
curl,jq, anddate(SKILL.md). - Sanitization: Absent; while the skill instructs the agent to filter fields with
jqrather than outputting raw JSON, it does not specify sanitization for text fields like notes or descriptions.
Audit Metadata