skills/garethmanning/education-agent-skills/explicit-instruction-sequence-builder/Gen Agent Trust Hub
explicit-instruction-sequence-builder
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable scripts, binaries, or shell commands. It is a purely instruction-based prompt template for pedagogical content generation.
- [SAFE]: No network access, remote downloads, or data exfiltration patterns were detected. All external references are to established academic educational frameworks and researchers (e.g., Rosenshine, Hattie).
- [SAFE]: No sensitive file paths, environment variables, or hardcoded credentials are used or requested by the skill. The inputs are restricted to classroom context data.
- [SAFE]: No obfuscation, hidden characters, or multi-layer encoding techniques were found in the prompt or documentation.
- [SAFE]: While the skill processes untrusted user input through variables like 'skill_to_teach', the skill has no access to sensitive capabilities or tools (no network, no file system write, no subprocess), which mitigates the risk of indirect prompt injection. There are no boundary markers or sanitization, but there is also no capability to exploit.
Audit Metadata