skills/okharedia/my-skills/teach-me/Gen Agent Trust Hub

teach-me

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from sources such as URLs, videos, articles, and repositories to generate teaching content.\n
  • Ingestion Point: User-provided materials are consumed as the primary syllabus as described in the Intake section of SKILL.md.\n
  • Capability Inventory: The agent has the ability to write to the filesystem (notes/book.md) and execute shell commands (git commit).\n
  • Boundary Markers: There are no instructions to use delimiters or ignore embedded instructions within the source material.\n
  • Sanitization: The skill does not describe any sanitization or validation procedures for the external content before it is interpolated into the teaching context.\n- [COMMAND_EXECUTION]: The skill utilizes automated shell commands to maintain a notebook of the learner's progress.\n
  • Autonomous Execution: The instructions provide standing permission to perform git commit operations without seeking user confirmation ("Do not wait to be asked"), which reduces oversight of modifications to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 05:06 AM
Security Audit — agent-trust-hub — teach-me