react-best-practices
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to analyze user-provided codebases, which serves as an untrusted data ingestion point.
- Ingestion points: Uses
Glob,Grep, andReadtools on files within a provided project path (e.g., inSKILL.mdandscripts/react_performance_checker.pyreferences). - Boundary markers: The instructions do not define clear delimiters or include warnings for the agent to ignore embedded instructions in the analyzed code.
- Capability inventory: The skill allows the use of
Bash,Write, andEdittools, which could be misused if an attacker embeds malicious instructions in the code being reviewed. - Sanitization: No evidence of content sanitization or validation before processing user-provided code.
- Unverifiable Dependencies (SAFE):
SKILL.mdreferences an automated audit script (scripts/react_performance_checker.py) that is not included in the provided files. While this creates an unverifiable capability, it appears to be a documentation oversight rather than a malicious trap.
Audit Metadata