skills/boom-vitt/skills-thai/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the gh issue create command to interact with GitHub. This is the primary intended function of the skill to automate issue reporting.
  • [PROMPT_INJECTION]: The skill incorporates untrusted user-provided bug descriptions into generated GitHub issues, which represents an indirect prompt injection surface.
  • Ingestion points: User narratives and problem descriptions collected during the interactive session (SKILL.md).
  • Boundary markers: Absent; user input is directly interpolated into structured Markdown templates.
  • Capability inventory: Execution of gh issue create to write data to external GitHub repositories.
  • Sanitization: No explicit sanitization, escaping, or validation of user-provided content is defined before the issue is created.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 12:51 PM
Security Audit — agent-trust-hub — qa