lwy-project-skill-installer
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs packages from external registries, including a community registry (skills.sh) and a scoped registry (@tiktok-fe/skills). It specifically suggests the global installation of the find-skills package using npx.
- [COMMAND_EXECUTION]: The skill uses npx to execute commands for searching and adding skills to the project. This includes npx skills find and npx skills add, which execute code fetched from remote repositories.
- [REMOTE_CODE_EXECUTION]: By design, the skill facilitates the execution of remote code by installing and adding AI agent skills (which contain executable instructions and scripts) from external sources into the local project environment.
- [PROMPT_INJECTION]: The skill scans project files (e.g., package.json, README, workflows) to build a 'Tech Profile'. This creates an ingestion surface for untrusted project data that could potentially influence agent behavior.
- Ingestion points: Project configuration and source files identified during the 'L2: Project Analysis' phase.
- Boundary markers: None identified in the instructions to prevent the agent from following instructions embedded in the scanned files.
- Capability inventory: Subprocess execution via npx and file system writes during the installation phase.
- Sanitization: No explicit sanitization or validation of the scanned file contents is mentioned before processing.
Audit Metadata