skills/google/filament/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Command Execution]: The skill instructs the agent to use version control commands such as git diff and git log to identify changes in the code base. These operations are standard components of a development workflow and are necessary for the skill's purpose. Because these commands may incorporate user-provided branch names or commit identifiers, they represent a routine command execution surface used within the context of source code analysis.
  • [Indirect Prompt Injection Surface]: Since the skill's primary function is to analyze external code, branches, and pull requests, it naturally interacts with untrusted data. This presents a common security surface where malicious code could potentially contain instructions aimed at influencing the agent. The skill's highly specific technical pillars and structured reporting format provide a clear scope that mitigates the risk of the agent following extraneous instructions found within the code being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 06:50 PM
Security Audit — agent-trust-hub — code-review