skills/0xbigboss/claude-code/tilt/Gen Agent Trust Hub

tilt

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines several shell-based workflows for environment management. It uses tilt for resource lifecycle and tmux for session persistence. The implementation includes logic to dynamically name tmux sessions based on the current git repository root and safely manage windows to avoid duplication.\n- [PROMPT_INJECTION]: The skill interacts with untrusted external data by reading container logs (tilt logs) and resource statuses (tilt get uiresources). This introduces a surface for indirect prompt injection where malicious log content could attempt to influence the agent's reasoning.\n
  • Ingestion points: Container logs via tilt logs and resource metadata via tilt get uiresources in SKILL.md and CLI_REFERENCE.md.\n
  • Boundary markers: None identified in the provided command patterns.\n
  • Capability inventory: Significant capabilities including tilt up/down/trigger and the ability to send arbitrary keys to a tmux session (tmux send-keys).\n
  • Sanitization: No evidence of output sanitization or filtering of log content before analysis.\n- [SAFE]: References to external repositories for Tilt extensions (tilt-dev/tilt-extensions) target well-known and official project sources, which is appropriate for the skill's documented purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:19 AM