issue-creation

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input from bug reports and feature requests, which is then interpolated into shell-based GitHub CLI commands.
  • Ingestion points: Fields such as Bug Description, Steps to Reproduce, Expected/Actual Behavior, and Relevant Logs defined in SKILL.md are populated by user input.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' directives to prevent the agent from obeying instructions embedded within user reports or logs.
  • Capability inventory: The skill utilizes the gh (GitHub CLI) tool via subprocess calls (gh issue create, gh issue edit) to modify repository state.
  • Sanitization: Absent. There are no instructions provided to escape, filter, or validate user-provided strings before they are passed to the command-line interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 12:24 AM
Security Audit — agent-trust-hub — issue-creation