code-setup-project
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs command execution to manage the environment setup, including
chmod +xto enable execution of wrapper scripts andnix flake checkto validate the integrity of the generated Nix configuration. - [EXTERNAL_DOWNLOADS]: The provided Nix flake template includes dependencies on external sources, specifically the official NixOS/nixpkgs repository and the flake-utils library from numtide, both of which are hosted on GitHub.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from project configuration files to automate setup recommendations.
- Ingestion points: Files like
package.json,pyproject.toml,setup.py,go.mod,Cargo.toml,Gemfile,Makefile, andCMakeLists.txtare parsed for project type and dependency detection. - Boundary markers: The analysis process does not implement specific delimiters or instructions to ignore instructions embedded within the metadata of these files.
- Capability inventory: The agent is capable of creating executable bash scripts, modifying file system permissions, and running Nix evaluation tools.
- Sanitization: The skill lacks explicit sanitization or validation steps for the command strings and package names extracted from the ingested project files before using them in generated outputs.
Audit Metadata