next-lesson

Pass

Audited by Gen Agent Trust Hub on Oct 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently executes the altitude CLI tool to manage tasks, monitor file changes, and report progress. It includes logic to detect the host platform and shell (Windows, macOS, Linux) to ensure commands are compatible. One specific command, altitude lesson open, is noted to start a local server, which is part of the interactive lesson functionality.
  • [DATA_EXFILTRATION]: Progress data, learner answers, and session metadata are sent to the Altitude server via the altitude emit command suite. This is the documented behavior for the 'Paid mode' of the learning project and is scoped to the specific learning session.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from learner messages and plan files. It implements a mitigation strategy by instructing the agent to wrap all learner-supplied text in single quotes and escape interior quotes when executing shell commands to prevent command injection.
  • [EXTERNAL_DOWNLOADS]: If the required CLI tool is missing, the skill provides instructions for the user to install the @learnaltitude/cli package from the npm registry, which is a standard procedure for this platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 14, 2026, 08:50 PM