skills/nanobei/skills/teach/Gen Agent Trust Hub

teach

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill architecture relies on reading and incorporating content from external files such as MISSION.md, RESOURCES.md, and GLOSSARY.md to author lesson artifacts.
  • Ingestion points: Data enters the agent's context through the reading of user-defined or externally-sourced markdown files in the workspace (e.g., RESOURCES.md).
  • Boundary markers: The skill lacks explicit instructions or delimiters that would prevent the agent from accidentally executing instructions hidden within the descriptions or metadata of the resources it processes.
  • Capability inventory: The skill allows for the creation and modification of workspace files (HTML, Markdown, CSS) based on the processed content.
  • Sanitization: There are no specified procedures for sanitizing or escaping content retrieved from external sources before it is interpolated into new lesson files or future instructional prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 01:53 PM
Security Audit — agent-trust-hub — teach