temet-run-tui-patterns

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements patterns for reading and displaying data from external agent processes via Inter-Process Communication (IPC). This establishes a potential surface for indirect prompt injection.\n
  • Ingestion points: Data enters the system context through the IPCClient.execute_command method in SKILL.md.\n
  • Boundary markers: Absent. The provided code templates do not demonstrate the use of delimiters or specific instructions for the agent to ignore embedded commands in the processed data.\n
  • Capability inventory: The skill environment is granted Bash, Read, Write, and Edit capabilities, which could be leveraged if the LLM follows instructions injected via the agent's output.\n
  • Sanitization: No sanitization, validation, or escaping of the streamed IPC content is included in the demonstrated patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:31 PM