skills/ahgraber/skills/teach-me/Gen Agent Trust Hub

teach-me

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocesses to execute git diff, git show, and gh pr diff to retrieve code context for generating lessons on specific changes.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from multiple sources and interpolates them into generated artifacts.
  • Ingestion points: Data enters the context via local codebase files (SKILL.md), git diff/show output (references/code-change.md), GitHub PR diffs, and external research results from supplementary skills.
  • Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate untrusted data within the prompt or output artifacts.
  • Capability inventory: The skill has the capability to read from and write to the local file system (saving artifacts to .teach/) and execute git-related shell commands.
  • Sanitization: There are no explicit sanitization or escaping instructions provided for handling untrusted code or research data before it is rendered into HTML or Markdown artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:11 PM
Security Audit — agent-trust-hub — teach-me