cost-booster-edit
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a Bash-invoked Node.js command to execute its transformation logic. It passes code and intent data as command-line arguments, which is a standard method for interacting with CLI tools.
- [PROMPT_INJECTION]: The skill processes file content and transformation intents, which constitutes a surface for indirect prompt injection. This risk is inherent to code-transformation tasks and is mitigated by a confidence-scoring system that rejects transformations with a confidence level below 0.5.
- Ingestion points: Reads source code from local files and accepts transformation 'intents' as arguments.
- Boundary markers: None identified in the prompt templates.
- Capability inventory: File system access (read/write) and shell execution via Bash.
- Sanitization: Uses the AgentBooster engine's confidence scoring to validate transformations before writing back to the file system.
Audit Metadata