skills/laststance/skills/bulk-issues/Gen Agent Trust Hub

bulk-issues

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill interacts with untrusted external data by reading GitHub issue descriptions, labels, and comments, and by processing pull request review threads. This content is used to inform code changes and implementation plans. \n
  • Ingestion points: Issue metadata via gh issue view and PR review threads via GraphQL. \n
  • Boundary markers: None explicitly defined in instructions. \n
  • Capability inventory: The skill has broad capabilities including file system modification, shell command execution (pnpm, git, gh), and network access. \n
  • Sanitization: Relies on the agent's internal reasoning gates and a human-in-the-loop approval step during the triage phase to mitigate risks. \n- [COMMAND_EXECUTION]: The skill performs shell operations using standard tools (git, gh, pnpm) for repository management, testing, and building. These commands are essential to the skill's primary function and are executed within the local project context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 03:29 AM
Security Audit — agent-trust-hub — bulk-issues