simplify

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [Prompt Injection] (LOW): The skill exhibits an indirect prompt injection surface by ingesting and processing source code files from the local environment.
  • Ingestion points: Uses git diff in SKILL.md to identify files which are then passed to a subagent.
  • Boundary markers: Instructions passed to the code-simplifier subagent do not use delimiters to wrap the content being analyzed, making it easier for embedded instructions in the code to influence the agent.
  • Capability inventory: The skill queries repository metadata and delegates code modification to a subagent.
  • Sanitization: No sanitization is performed on the code content before it is processed by the LLM.
  • [Command Execution] (SAFE): Employs git and gh commands for repository state inspection. These commands are static and do not incorporate unvalidated user input into the shell execution string.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:44 PM