scaffolded-task-modifier
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a purely text-based generator for educational scaffolding. It does not utilize any external tools, perform network operations, or access the file system.
- [PROMPT_INJECTION]: The skill processes user-provided content such as
original_taskandstudent_profiles. While this creates a surface for indirect prompt injection (where a user might provide text intended to override the agent's instructions), the risk is negligible as the skill lacks access to sensitive data or dangerous system capabilities. The impact is limited to the quality of the generated text output. - [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive credentials were found in the skill manifest or prompt instructions.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or refer to untrusted remote scripts. All references are to academic literature for instructional context.
Audit Metadata