lightrun-runtime-aware-pr-review
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (
gh api) to programmatically fetch pull request details and diff data. These operations target the official GitHub API and are fundamental to the skill's purpose of code review. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from GitHub pull request diffs and captures production runtime data via the Lightrun MCP.
- Ingestion points: Pull request diffs (via
gh api) and variable values captured from production environments (vialightrunMCP tools). - Boundary markers: The process is governed by a structured multi-phase workflow defined in the skill's reference files.
- Capability inventory: Includes the ability to interact with the GitHub API and production runtime through snapshots.
- Sanitization: There are explicit, mandatory instructions to sanitize all captured runtime evidence, ensuring that secrets, tokens, and identifiers are redacted before being included in the final report.
- [SAFE]: All external communications, including instrumentation and telemetry, are directed to the vendor's official domain (
lightrun.com). The skill explicitly prohibits state-changing instrumentation and mandates strict data sanitization, minimizing risks associated with production data access.
Audit Metadata