amplifier-config

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution and File System Interaction: The skill is designed to modify configuration files across different scopes (global, project, local) and execute CLI commands. It includes safety-oriented guidelines for these operations, such as performing atomic writes via temporary files and preserving original file permissions.
  • Indirect Prompt Injection Surface: The skill functions by reading and interpreting external data from configuration files and CLI tool outputs, which represents an ingestion point for untrusted content.
  • Ingestion points: Effective configuration files, provenance traces, and output from the app-cli:cli-expert tool.
  • Boundary markers: The instructions do not specify explicit delimiters for separating ingested configuration data from the agent's instructions.
  • Capability inventory: The skill possesses the ability to write to files and execute system commands to apply configuration changes.
  • Sanitization: There are explicit, mandatory instructions to redact sensitive information including API keys, tokens, and authorization headers before any output or delegation occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 04:27 AM
Security Audit — agent-trust-hub — amplifier-config