skills/agentivestack/skills/qa/Gen Agent Trust Hub

qa

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automates the creation of GitHub issues using the gh issue create command. It explicitly instructs the agent to "file and share URLs without asking for review first," which bypasses standard human-in-the-loop confirmation for actions with external impact.
  • [SAFE]: The skill includes strong negative constraints intended to prevent data exposure, specifically directing the agent to use domain-specific language and avoid including file paths, line numbers, or implementation details in the generated issues.
  • [SAFE]: File access is limited to reading project documentation (e.g., docs/UBIQUITOUS_LANGUAGE.md, docs/CONTEXT_MAP.md) to establish context for the issue reports.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 10:36 PM