laravel-simplifier
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes recently modified code as input, creating a surface for indirect prompt injection attacks where instructions hidden in the code could hijack the agent's logic.
- Ingestion points: The skill analyzes and refines "recently modified code sections" (SKILL.md).
- Boundary markers: The instructions do not define delimiters or provide warnings for the agent to ignore instructions found within comments or strings in the analyzed code.
- Capability inventory: The skill is designed to refactor and modify the codebase, implying file-write and file-read capabilities.
- Sanitization: No sanitization or verification process is defined to filter out natural language instructions embedded within source files.
- Risk Factor: The instruction to "operate autonomously and proactively... without requiring explicit requests" reduces human oversight, increasing the risk that a successful injection could modify the project without user approval.
Audit Metadata