repomix

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading remote repository content from GitHub or other Git providers using the repomix tool's --remote feature. This is documented as a core capability for analyzing third-party libraries.- [COMMAND_EXECUTION]: The helper script scripts/repomix_batch.py executes the repomix and npx CLI tools using subprocess.run(). The command is constructed as a list of arguments, which is a secure practice that prevents shell injection vulnerabilities.- [DATA_EXFILTRATION]: The script contains logic to load environment variables from .env files located in the skill's directory tree. This is a standard configuration pattern used to pass necessary credentials to the underlying tools.- [PROMPT_INJECTION]: As the skill is designed to ingest and package entire codebases for LLM context, it has a large attack surface for Indirect Prompt Injection. The skill includes explicit security considerations and recommends the use of its built-in security scanner to mitigate this risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 01:37 AM
Security Audit — agent-trust-hub — repomix