renovate-migrate

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it retrieves migration instructions ('Required Code Changes') from external GitHub PR comments using the gh CLI tool. An attacker could potentially embed malicious instructions in a PR comment that the agent might execute while attempting to perform code migrations.
  • Ingestion points: GitHub PR comments and PR body (SKILL.md).
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within the fetched content.
  • Capability inventory: The skill has file modification capabilities (Edit, Write tools) and shell execution capabilities (Bash tool for pnpm and git).
  • Sanitization: Absent; the content retrieved from the PR is not validated or sanitized before being used to guide the agent's actions.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute several commands including gh, git, and pnpm. While these are standard tools for the intended task, the execution flow is guided by instructions parsed from external and untrusted PR data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:39 AM
Security Audit — agent-trust-hub — renovate-migrate