laravel-simplifier
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (HIGH): The skill possesses a high-risk attack surface by combining untrusted data ingestion with file-modification capabilities.
- Ingestion points: The skill reads local file paths and git diff outputs provided as inputs (specified in the 'Inputs' section of SKILL.md).
- Boundary markers: No delimiters or explicit instructions are provided to help the agent distinguish between the code content it is analyzing and the instructions it must follow.
- Capability inventory: The workflow includes a step to 'apply minimal edits and keep changes localized,' indicating the agent has write access to the filesystem.
- Sanitization: There is no mention of sanitizing or escaping the content read from files, nor are there warnings to ignore natural language instructions found within the code (e.g., within PHP comments).
Recommendations
- AI detected serious security threats
Audit Metadata