code-simplifier
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands to run local utility scripts within the agent's environment, such as
node .claude/scripts/ai-signal-scan.cjsfor identifying AI-related code andpython .claude/scripts/code_graphfor tracing code dependencies. - [INDIRECT_PROMPT_INJECTION]: The skill's core function involves reading and analyzing project source code, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: Project source files, configuration files (e.g., docs/project-config.json), and documentation identified during the analysis phase (SKILL.md).
- Boundary markers: Absent; the instructions do not specify the use of delimiters or safety prompts to isolate the content of the analyzed files from the agent's control logic.
- Capability inventory: The skill can orchestrate sub-agents via
spawn_agentand execute local shell commands for script-based analysis (SKILL.md). - Sanitization: Absent; there are no explicit steps to sanitize or validate the content of the code files before they are processed by the agent.
Audit Metadata