perma-based-lesson-designer

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is entirely instructional and does not perform any dangerous operations such as command execution or network access. All references and academic framework citations are legitimate and safe.
  • [NO_CODE]: This is a text-based skill consisting of metadata and prompt instructions. No scripts, binaries, or automated tools are included.
  • [PROMPT_INJECTION]: The skill utilizes input parameters like 'lesson_content' and 'student_profiles' which are interpolated into the prompt. Ingestion points: Inputs are directly included in the prompt template in SKILL.md. Boundary markers: No delimiters are used to separate user data from system instructions. Capability inventory: The skill has no access to subprocesses, shell commands, file writing, or network tools. Sanitization: No validation or escaping is applied to inputs. While this creates a surface for indirect prompt injection, the lack of dangerous capabilities limits the risk to text generation only.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:23 AM
Security Audit — agent-trust-hub — perma-based-lesson-designer