code-review

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands like git diff and git show to determine the scope of changes and mandates the execution of project-specific test and lint commands to verify fixes. Running arbitrary project scripts carries an inherent risk of executing malicious code if the project environment is compromised.
  • [INDIRECT_PROMPT_INJECTION]: The agent processes untrusted input in the form of code diffs and file contents. A malicious diff could contain embedded instructions designed to influence the agent's behavior during the review or verification phase.
  • Ingestion points: Source code files and git diff output (SKILL.md).
  • Boundary markers: Absent. The instructions do not specify delimiters or techniques to isolate untrusted code content from agent instructions.
  • Capability inventory: The skill possesses the ability to modify local files and execute shell commands (SKILL.md).
  • Sanitization: None. The skill does not describe any validation or sanitization of the code it reads before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 04:30 PM
Security Audit — agent-trust-hub — code-review