practice-problem-sequence-designer
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and metadata were analyzed, and no malicious patterns, obfuscation, or attempts to bypass safety guidelines were detected. The skill's behavior is consistent with its stated purpose of pedagogical task design.
- [PROMPT_INJECTION]: No evidence of direct prompt injection, system prompt extraction, or safety filter bypass techniques was found in the prompt instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests untrusted data from external variables like student profiles and prior examples.
- Ingestion points: Prompt template variables such as
{{student_profiles}},{{prior_examples}}, and{{common_errors}}inSKILL.md. - Boundary markers: Absent; the skill does not use delimiters to isolate untrusted input from its core instructions.
- Capability inventory: The skill's defined workflow is limited to generating formatted text output; it does not request or utilize tools for file system access, network communication, or shell execution.
- Sanitization: No input sanitization or validation logic is present in the prompt to filter potentially malicious instructions within the variables.
- [REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of remote scripts or unverified packages.
Audit Metadata