pj-init
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes standard shell commands such as
pwd,ls, andgit remoteto identify repository structures and project metadata. These operations are local and do not involve elevated privileges or remote command execution. - [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) as it processes data from untrusted local files to generate the
CLAUDE.mdworkspace configuration. - Ingestion points: File contents from
README,package.json, andpyproject.tomllocated in subdirectories. - Boundary markers: Absent; the skill does not use delimiters or instructions to prevent the agent from obeying commands embedded within the analyzed project files.
- Capability inventory: Local shell command execution (
git) and file system write access (CLAUDE.mdgeneration andldocinitialization). - Sanitization: Absent; the skill extracts strings from local files and interpolates them directly into templates.
Audit Metadata