skills/nvidia/elements/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a standard senior code reviewer persona to provide feedback on code quality, testing, and documentation. It operates on local repository data (Git staged files) and internal project documentation.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted data (source code changes) provided by the user.
  • Ingestion points: Git staged files and the latest branch commits (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify delimiters to isolate the content of the reviewed files from the agent's logic.
  • Capability inventory: The skill utilizes file reading and repository metadata inspection. No explicit network operations, subprocess executions, or file-write capabilities are defined in the skill content.
  • Sanitization: Absent. The skill does not provide instructions for escaping or filtering the ingested code content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 08:13 AM
Security Audit — agent-trust-hub — code-review