alert-triage

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill instructions and reference materials promote standard security investigation procedures and do not contain any malicious instructions, obfuscation, or unauthorized access attempts.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential attack surface due to the processing of external alert data alongside tools with query and write capabilities. This surface is inherent to its primary purpose as an alert triage tool.
  • Ingestion points: The triage-alerts tool fetches external data including rule names, hostnames, and process details into the agent context as described in SKILL.md.
  • Boundary markers: There are no explicit instructions for using delimiters or boundary markers when handling alert data returned from the tool.
  • Capability inventory: The agent can perform database-like writes via the manage-cases tool and execute ES|QL queries through the threat-hunt tool across its operations.
  • Sanitization: No specific sanitization or input validation logic is detailed in the provided instructions for processing the alert content.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 08:27 AM