justfile-author

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The assets/Makefile.tmpl file contains a recipe to download the just task runner directly from its official domain at https://just.systems/install.sh. This uses a standard installation pattern (curl piped to bash) for this well-known developer tool.
  • [COMMAND_EXECUTION]: The skill workflow includes instructions for the agent to grant execution permissions to generated scripts using chmod +x. Additionally, the Makefile template includes commands to install software via system package managers like brew, cargo, and snap.
  • [PROMPT_INJECTION]: The skill logic involves reading command names and scripts from local project files (such as package.json or pyproject.toml) and interpolating them into generated task runner files. While this creates a surface for indirect prompt injection if project files contain malicious content, the behavior is localized and consistent with the skill's purpose as a scaffolding tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:47 PM
Security Audit — agent-trust-hub — justfile-author