clockwork-alert-router

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection through its data processing workflow.
  • Ingestion points: The skill ingests untrusted data from the output records of clockwork-compliance-check in references/workflows/alert-routing-workflow.md.
  • Boundary markers: There are no boundary markers or instructions to ignore embedded commands defined when processing the compliance records.
  • Capability inventory: The skill has the capability to send emails via Gmail MCP and create or update issues via the mcp-atlassian Jira MCP, as defined in SKILL.md.
  • Sanitization: No evidence of sanitization, escaping, or validation of the ingested compliance data is present before it is interpolated into notification templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 06:37 AM