to-tickets

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external files to generate tickets.
  • Ingestion points: Reads user-provided specifications, conversation history, and the existing repository codebase.
  • Boundary markers: The instructions do not define specific delimiters for external content within the generated output.
  • Capability inventory: The skill can write markdown files to the local file system (docs/tickets/) and interact with the GitHub API to create issues.
  • Sanitization: No specific sanitization methods are mentioned, though a mandatory human-in-the-loop approval step is required.
  • [SAFE]: No signs of malicious behavior, data exfiltration, obfuscation, or unauthorized command execution were found. The skill is purely instructional and emphasizes user verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 08:50 AM
Security Audit — agent-trust-hub — to-tickets