senior-frontend
Fail
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The component generator script exposes a significant attack surface by taking user-controlled input and performing file system operations without sanitization.
- Ingestion points: The
nameand--dirarguments inscripts/component_generator.pyare intended to be populated by the agent based on user requests. - Boundary markers: None. There are no delimiters or instructions to the agent to treat these inputs as literal or restricted.
- Capability inventory: The script uses
pathlib.Path.mkdir(parents=True)andPath.write_text()to create directories and write files to the disk. - Sanitization: None. The script does not use any path validation or 'realpath' checks to ensure that the generated files remain within a designated workspace. A malicious user could provide a component name like
../../../../tmp/maliciousto write files outside of the project root.
Recommendations
- AI detected serious security threats
Audit Metadata