language-demand-analyser
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests multiple user-controlled strings and interpolates them directly into the prompt without boundary markers or sanitization, creating a surface for prompt injection.
- Ingestion points: The prompt section in SKILL.md uses template variables
{{task_description}},{{student_level}},{{subject_area}},{{language_proficiency}},{{student_profiles}},{{task_materials}}, and{{prior_language_instruction}}to process external data. - Boundary markers: Absent. Input data is presented as plain text labels (e.g.,
Task: {{task_description}}) without delimiters or instructions to the model to ignore embedded commands within the input fields. - Capability inventory: The skill identifies no enabled capabilities for file system access, network operations, subprocess execution, or dynamic code evaluation.
- Sanitization: No sanitization, escaping, or schema validation is performed on the input strings before they are processed by the model.
Audit Metadata