system-design-mock

Warn

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the shell command date +%s to track the duration of the mock interview session.
  • [DYNAMIC_EXECUTION]: The agent is instructed to perform runtime compilation and linting of code skeletons provided by the candidate using command definitions found in an external reference file ../oa-sim/RUNNER.md. It also involves generating and running concurrency tests and reporting their results.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted user input which is subsequently utilized in code execution and diagram generation tasks. 1. Ingestion points: User-provided design requirements and code skeletons within the session. 2. Boundary markers: The instructions lack specific delimiters to isolate user input from the agent's logic. 3. Capability inventory: The skill can execute shell commands and trigger external compilers and testing tools. 4. Sanitization: No evidence of validation or sanitization of user-provided code before execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 10, 2026, 06:31 AM