justfile-author

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The Makefile template includes a command to download and execute the official installation script for the just task runner from the official domain at https://just.systems/install.sh.\n- [COMMAND_EXECUTION]: Automates the setting of executable permissions using chmod +x for generated service scripts and executes local validation commands including just --list and make help to verify the success of the scaffolding process.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from project configuration files and interpolating it into generated shell scripts and justfile recipes.\n
  • Ingestion points: Project configuration files such as package.json, Cargo.toml, pyproject.toml, and go.mod.\n
  • Boundary markers: None present in the generated templates to delimit external data from instruction blocks.\n
  • Capability inventory: File system writes, permission modification via chmod, and local command execution of just and make.\n
  • Sanitization: Basic slug normalization (lowercase and underscore replacement) is applied to project titles, but command strings from scripts are interpolated without specific escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:22 PM
Security Audit — agent-trust-hub — justfile-author