triage-issue

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads untrusted data from user reports and codebase files to automatically generate GitHub issues.
  • Ingestion points: User-provided bug descriptions and codebase source files accessed during diagnosis.
  • Boundary markers: Absent. The instructions specifically tell the agent to minimize questions and create issues without user review, which reduces human oversight of potentially malicious or deceptive input content.
  • Capability inventory: Use of the Agent tool (Explore type) for codebase exploration and the GitHub CLI (gh issue create) for external issue creation.
  • Sanitization: No explicit sanitization or validation of gathered input is performed before it is formatted into the issue template.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 04:26 PM
Security Audit — agent-trust-hub — triage-issue