tilt-dev

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands using the tilt CLI and provided shell scripts (check_tilt_status.sh, get_service_health.sh) to monitor and manage services.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface where the agent processes potentially untrusted output from local service logs and health check responses.\n
  • Ingestion points: Service logs retrieved via tilt logs and response bodies from curl health checks in scripts/get_service_health.sh.\n
  • Boundary markers: Absent; the skill does not use delimiters or instructions to notify the agent that service output should be treated as untrusted data.\n
  • Capability inventory: The skill provides capabilities to execute tilt commands and shell scripts based on agent decisions.\n
  • Sanitization: Absent; no escaping or validation is performed on the output from local services before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 06:06 AM