error-boundary-generator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing untrusted data (user source code) which can influence the agent's behavior and file generation output.
- Ingestion points: The agent reads React component files, route definitions (e.g.,
page.tsx), and a local configuration file (config/defaults.md). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the analyzed code strictly as data or to ignore any natural language instructions that might be embedded within the source files.
- Capability inventory: The skill identifies gaps and generates several types of files (
error.tsx,loading.tsx,not-found.tsx,global-error.tsx) using the agent's file-writing capabilities. - Sanitization: The process lacks validation or sanitization steps to ensure that content extracted from the analyzed files does not contain malicious prompt injections that could alter the generated output or subsequent agent actions.
Audit Metadata