code-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- PROMPT_INJECTION (LOW): Potential for Indirect Prompt Injection. The skill is designed to read and analyze arbitrary source code files provided by the user.
- Ingestion points: Content of files targeted by the
/review-code <file-path>command (SKILL.md). - Boundary markers: Absent. The instructions do not specify delimiters or provide a system prompt directive to ignore executable instructions within the analyzed data.
- Capability inventory: The agent has access to
Read,Bash, andGreptools, which could be exploited if the agent obeys instructions found within a reviewed file. - Sanitization: Absent. The skill provides no mechanism to filter or sanitize the content of the files before processing.
- COMMAND_EXECUTION (SAFE): The skill is granted the
Bashtool. While this is a high-privilege tool, the skill itself does not contain any pre-defined malicious commands or suspicious execution patterns. - NO_CODE (SAFE): The skill consists entirely of markdown-based documentation and instructions. It does not include Python scripts, binaries, or other executable files that could harbor malware.
Audit Metadata