code-simplifier
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and modifying code, creating a surface for potential indirect prompt injection attacks.
- Ingestion points: The skill explicitly identifies and analyzes recently modified code sections from the current session or repository files for refinement.
- Boundary markers: There are no explicit instructions or delimiters defined to isolate the processed code from the agent's internal instructions, nor are there warnings to ignore embedded directives within the code comments.
- Capability inventory: The skill is capable of performing code refactoring and modifications based on its analysis, which could be influenced by instructions hidden within the data it processes.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation steps for the input code before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill documentation includes a reference to Anthropic's official Claude plugins repository for its underlying logic.
- Evidence: The file contains a reference to the code-simplifier agent documentation at
https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md.
Audit Metadata