github-goal-issue-triage

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub, which presents a surface for indirect prompt injection attacks.
  • Ingestion points: The skill fetches GOAL.md files and issue metadata (titles, bodies, comments) from external GitHub repositories as described in the Repository Workflow section of SKILL.md.
  • Boundary markers: The instructions lack explicit delimiters to separate untrusted repository content from the agent's internal logic, although the agent is directed to follow a specific priority rubric.
  • Capability inventory: The skill has capabilities to create and update GitHub labels via the API and write a local HTML report file to the current working directory.
  • Sanitization: The skill mandates the use of an escapeHtml() helper for all dynamic values in the HTML report to prevent XSS, demonstrating a proactive security posture regarding the handling of untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 07:27 PM
Security Audit — agent-trust-hub — github-goal-issue-triage