skills/kitlangton/motel/motel-debug/Gen Agent Trust Hub

motel-debug

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes bunx @kitlangton/motel start to download and execute the Motel server from the NPM registry if it is not already present on the user's PATH. This package originates from the skill author's verified namespace.
  • [COMMAND_EXECUTION]: Executes shell commands including motel start, motel status, and curl to manage the local telemetry daemon and query traces and logs from the loopback interface (127.0.0.1).
  • [PROMPT_INJECTION]: Exhibits a surface for indirect prompt injection because the agent is instructed to ingest and analyze log and span data which may contain content from the application being debugged.
  • Ingestion points: Data retrieved via GET /api/logs/search and GET /api/spans/search as described in the 'Analyze evidence' section of SKILL.md.
  • Boundary markers: Absent; the agent is not provided with explicit delimiters to distinguish telemetry data from its own instructions.
  • Capability inventory: Subprocess execution via motel start and file system modification through the scripts/clear-motel-debug.ts script.
  • Sanitization: None; the skill does not include steps to sanitize or escape telemetry content before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:40 AM