aile-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local Git commands (git rev-parse, git log, git diff) to identify code changes and retrieve their content. These commands are necessary for the skill's primary function and do not use elevated privileges.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted code content from a Git repository.
  • Ingestion points: code-reviewer.md instructs the agent to execute git diff and review the resulting output, which contains arbitrary code changes.
  • Boundary markers: Absent. The template does not utilize specific delimiters or a system instruction to ignore embedded natural language instructions within the code diff.
  • Capability inventory: The skill has the capability to read local file content via git and output a structured assessment.
  • Sanitization: Absent. The skill performs no filtering or sanitization of the code content before presenting it to the agent for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 04:18 AM