Skills
skills/xyenon/agents/kitty/Gen Agent Trust Hub

kitty

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use kitten @ launch and kitten @ send-text to execute shell commands and interact with terminal windows.
  • [DATA_EXFILTRATION]: The kitten @ get-text command is used to capture terminal output, which could potentially expose sensitive data displayed in the terminal session.
  • [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by reading terminal output which may contain untrusted data.
  • Ingestion points: kitten @ get-text as described in SKILL.md.
  • Boundary markers: Absent from the provided command examples.
  • Capability inventory: kitten @ launch and kitten @ send-text provide command execution capabilities.
  • Sanitization: No sanitization or validation of captured text is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 02:19 AM