skills/nweii/agent-stuff/build-lab/Gen Agent Trust Hub

build-lab

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The loader template provided in references/nextjs-scaffold.md implements dynamic import() to load meta.ts modules based on directory names discovered via fs.readdirSync. This pattern facilitates the execution of local files based on the filesystem structure.\n- [INDIRECT_PROMPT_INJECTION]: The registry system implements a data ingestion surface where metadata from local files influences the agent's context during future sessions. 1. Ingestion points: The loadLabEntries function in references/nextjs-scaffold.md discovers and imports metadata modules from subfolders. 2. Boundary markers: The instructions do not define specific delimiters or safety warnings for the imported metadata content. 3. Capability inventory: The ingested metadata is used to build the agent's understanding of available labs via the AGENTS.md / CLAUDE.md section. 4. Sanitization: There is no evidence of validation or filtering of the metadata fields before they are processed by the agent.\n- [COMMAND_EXECUTION]: The Setup instructions in SKILL.md require the agent to execute git mv shell commands to migrate existing project files as part of the initial configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 11:27 PM