typo3-simplify

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
  • Ingestion points: The skill identifies and reads local source code files (PHP, Fluid, TCA, Services.yaml) identified via git diff.
  • Boundary markers: There are no explicit instructions or delimiters used to separate the skill's logic from instructions that might be embedded within the files being analyzed.
  • Capability inventory: The skill is designed to read file contents and suggest or apply code modifications to the project.
  • Sanitization: No validation or sanitization is performed on the content of the analyzed files to prevent the agent from following embedded instructions.
  • [COMMAND_EXECUTION]: The skill utilizes the local command git diff --name-only HEAD~1 to identify modified files. While this is a standard and expected operation for a code review tool, it involves the execution of shell commands to interact with the system's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:01 AM