teach

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to open generated lesson files (HTML) using system CLI commands like 'open' or 'start'. While this involves interacting with the local shell, it is a standard convenience feature for developer-oriented tools.
  • [EXTERNAL_DOWNLOADS]: The agent is tasked with finding high-quality external resources, such as articles and books, to populate the workspace's knowledge base. This involves identifying and linking to third-party domains.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its ingestion of external resource data.
  • Ingestion points: External URLs and text content from resources documented in RESOURCES.md.
  • Boundary markers: The skill does not provide specific instructions or delimiters to isolate untrusted external content from the agent's core instructions.
  • Capability inventory: The agent has the capability to write HTML/JS files to the local assets and lessons directories and execute shell commands to open them.
  • Sanitization: There are no explicit requirements for the agent to sanitize or validate the content retrieved from external sources before inclusion in lessons.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:25 AM
Security Audit — agent-trust-hub — teach