skills/ulpi-io/skills/create-pr/Gen Agent Trust Hub

create-pr

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands (git, gh, npx) to manage repository state and create pull requests. These actions are aligned with the skill's stated purpose and use standard industry tools.
  • [PROMPT_INJECTION]: The skill processes untrusted data from git diffs and commit messages (ingestion point: git diff in SKILL.md). While boundary markers are not explicitly used in the prompt interpolation, the skill enforces a strict output schema and uses quoted HEREDOCs (<<'EOF') to sanitize data during command execution (gh pr create), mitigating risks associated with malicious content in the diff.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to run tsc and eslint. This involves well-known developer tools from the official npm registry, which is a standard and safe practice in modern development workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 05:48 PM