skills/grehnen/copilot-tooling/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill uses the GitHub CLI (gh issue create) to submit bug reports to an external repository. This is the intended primary function. The instructions include explicit safeguards, such as forbidding the inclusion of internal file paths or implementation details in the reports, which prevents accidental exposure of codebase structure.
  • [COMMAND_EXECUTION]: The skill utilizes the gh command-line tool to automate issue creation. This is a standard and legitimate use of developer tooling within the agent's expected workflow.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from user descriptions and the codebase to generate reports. It manages this risk by enforcing structured templates and directing the agent to focus strictly on user-facing behaviors rather than internal code structures.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 07:49 PM