skill-forge-quiz

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Node.js script (scripts/import_quiz.js) to process JSON files. This involves running shell commands with arguments derived from files created or provided at runtime.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection (Category 8).
  • Ingestion points: Data enters the agent's context through user-provided JSON files and results from web searches (specifically mentioning the search_web tool and Brave Search).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external or user-provided content.
  • Capability inventory: The skill can write files to the local filesystem (temporary JSON files) and execute commands via node.
  • Sanitization: No sanitization or strict schema validation is described for the content extracted from web searches or user files before it is saved and processed by the import script.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 09:45 PM