using-jj-workspaces
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes several shell commands to manage the Jujutsu version control system (e.g.,
jj workspace add,jj workspace root,jj new). It also executes arbitrary project commands for dependency installation and testing based on detected files. - [EXTERNAL_DOWNLOADS]: The skill triggers downloads from well-known package registries (npm, PyPI, Crates.io) when it detects manifest files like
package.jsonorrequirements.txt. These are standard development operations. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests data from local repository files to determine its behavior.
- Ingestion points: The skill reads
CLAUDE.mdfor project conventions and inspects manifest files (package.json,Cargo.toml,requirements.txt,pyproject.toml,go.mod) to decide which commands to run. - Boundary markers: No boundary markers or 'ignore embedded instructions' warnings are used when reading these files.
- Capability inventory: The skill can execute shell commands, perform network operations via package managers, and run arbitrary project test suites.
- Sanitization: No sanitization or validation is performed on the content of the configuration files before they influence execution paths.
Audit Metadata