skills/garethmanning/education-agent-skills/worked-example-to-problem-solving-transition-designer/Gen Agent Trust Hub
worked-example-to-problem-solving-transition-designer
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed entirely of a markdown file containing a prompt template and metadata. No scripts, binaries, or other executable files are included in the package.\n- [SAFE]: Technical analysis found no evidence of malicious patterns, obfuscation, or unauthorized access to system resources. The skill's functionality is strictly limited to text generation for educational purposes.\n- [PROMPT_INJECTION]: The skill processes user-supplied information about student state and target skills, creating an attack surface for indirect prompt injection.\n
- Ingestion points: User input for skill_being_taught and current_student_state is interpolated into the prompt template in SKILL.md.\n
- Boundary markers: The inputs are placed within designated text sections but lack explicit delimiters or safety instructions to ignore embedded commands.\n
- Capability inventory: The skill has no access to external tools, network requests, or file system modifications.\n
- Sanitization: No validation or sanitization is performed on user-supplied strings before interpolation.
Audit Metadata