fixing-react-antipatterns
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes external codebases where malicious instructions could be embedded. * Ingestion points: Files in the directory provided via the $ARGUMENTS variable. * Boundary markers: The skill does not instruct the agent to use specific delimiters or to disregard instructions found within files. * Capability inventory: The skill can modify local files and execute shell commands (e.g., bun run lint). * Sanitization: No explicit content sanitization is performed.
- [COMMAND_EXECUTION]: The skill executes a bundled shell script (scripts/scan-antipatterns.sh) and project-specific linting tools to perform its tasks.
Audit Metadata