skills/mikopbx/core/babel-compiler/Gen Agent Trust Hub

babel-compiler

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands using the docker run pattern. It instructs the agent to construct commands by interpolating file paths (sourced from the user or the filesystem) into a bash template. This dynamic construction presents a surface for command injection if the input paths contain shell metacharacters.
  • [EXTERNAL_DOWNLOADS]: The skill pulls the Docker image ghcr.io/mikopbx/babel-compiler:latest from the GitHub Container Registry. This image is a resource provided by the vendor and is hosted on a well-known service.
  • [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it processes external code files. Ingestion points: The skill uses the Read tool to ingest JavaScript source files from the project environment. Boundary markers: There are no specific delimiters or instructions used to distinguish the untrusted code content from the agent's instructions. Capability inventory: The agent has access to powerful tools including Bash, Read, and Glob. Sanitization: No sanitization or content validation is performed on the files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:15 AM
Security Audit — agent-trust-hub — babel-compiler