pagerduty-api

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (CRITICAL): Automated security scanning identified a phishing URL in 'references/resources/Teams.md', which constitutes a confirmed detection of malicious content. Additionally, the Automation Actions API ('references/schemas/Automation/AutomationActionsScriptActionDataReference.md') allows the creation and execution of arbitrary scripts on remote runners.
  • Data Exposure & Exfiltration (HIGH): The Webhook Subscription API ('references/schemas/Webhook/WebhookSubscription.md') allows data to be sent to any arbitrary external URL via HTTP POST, creating a high risk of exfiltration for sensitive incident and account information.
  • Indirect Prompt Injection (LOW): The skill presents a significant surface for indirect prompt injection attacks. Ingestion points: Untrusted data enters the agent context through 'listIncidents' and 'listIncidentNotes' operations ('references/operations/'). Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for data fetched from the API. Capability inventory: The skill includes powerful capabilities such as remote script execution and network-based webhook registration. Sanitization: There is no evidence of content sanitization or filtering before external data is processed by the model.
Recommendations
  • AI detected serious security threats
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 06:38 PM