coderabbit-cli

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the @coderabbitai/cli package via npm. This is the official tool for CodeRabbit, which is a well-known technology provider for AI-driven code reviews.
  • [COMMAND_EXECUTION]: The skill relies on coderabbit and git command execution to analyze repository changes and provide feedback. This is a core requirement for the tool's intended functionality.
  • [DATA_EXFILTRATION]: Local code changes are transmitted to CodeRabbit's infrastructure for analysis. This is documented as the primary function of the service and is expected behavior for a cloud-based code review tool.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface. 1. Ingestion points: Local source code and CodeRabbit CLI feedback (SKILL.md, references/cli-commands.md). 2. Boundary markers: Absent; there are no specific instructions to separate code content from instructions. 3. Capability inventory: The agent is capable of file-system writes and command execution to address feedback (SKILL.md). 4. Sanitization: Absent; no validation or filtering of the CLI output is required before the agent processes and applies suggestions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 11:53 AM
Security Audit — agent-trust-hub — coderabbit-cli