skills/keboola/ai-kit/reviewer/Gen Agent Trust Hub

reviewer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (LOW): The skill is granted access to the Bash tool and is explicitly instructed to execute git diff to retrieve code for analysis. This is a legitimate and necessary function for a code review agent in a developer environment.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it processes content from external files that could be controlled by an attacker.
  • Ingestion points: Content is ingested through the output of git diff and the reading of project files such as CLAUDE.md, pyproject.toml, and other source files.
  • Boundary markers: Absent. The instructions do not define clear delimiters or provide the model with specific warnings to ignore instructions found within the code or comments it reviews.
  • Capability inventory: The skill possesses powerful capabilities including Bash execution, Read (file access), Grep, and Glob (filesystem discovery).
  • Sanitization: Absent. The skill does not sanitize or filter the content of the files it reads before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:28 PM